© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 5464
    Prev
    Next
    INDEX
    Explanations

    mentions of specific topics or keywords related to agriculture, health, military meetings, community advocacy, documentaries, priesthood, forensic anthropology, and specific individuals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.18
    1.0%
    575
    +0.14
    0.8%
    326
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.18
    0.03
    288
    +0.14
    0.03
    575
    +0.09
    0.03
    Negative Logits
    aughtered
    -0.55
    ãĥ£
    -0.52
    actionDate
    -0.50
    ortium
    -0.50
    00200000
    -0.49
    cffffcc
    -0.47
    rss
    -0.47
    printed
    -0.46
    uristic
    -0.46
    utm
    -0.46
    POSITIVE LOGITS
     ecosystem
    0.54
    dom
    0.52
    cember
    0.52
    edom
    0.51
     universe
    0.50
     outweigh
    0.49
    $.
    0.48
     initiation
    0.48
    iste
    0.48
     fundamentals
    0.47
    Activations Density 0.044%

    No Known Activations