© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 14086
    Prev
    Next
    INDEX
    Explanations

    the word "contain" along with other related terms

    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
    59
    +0.21
    0.8%
    167
    +0.17
    0.6%
    608
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.21
    0.05
    455
    +0.17
    0.07
    730
    +0.13
    0.05
    Negative Logits
    doms
    -1.06
    heit
    -0.92
    alm
    -0.89
     Sabha
    -0.88
    yrim
    -0.86
     Seym
    -0.84
    mare
    -0.83
    si
    -0.82
    hon
    -0.81
    ifact
    -0.80
    POSITIVE LOGITS
    ãĤ£
    1.07
    ttes
    1.05
    nces
    1.01
    encies
    0.89
    ÃįÃį
    0.88
    ãĤ·ãĥ£
    0.87
    vier
    0.86
    capacity
    0.86
    xual
    0.85
    CONT
    0.85
    Activations Density 1.497%

    No Known Activations