© 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. 14098
    Prev
    Next
    INDEX
    Explanations

    information related to medical diagnostics and procedures, such as codes and descriptions

    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
    680
    +0.03
    0.5%
    437
    +0.03
    0.4%
    581
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    723
    +0.03
    0.01
    231
    +0.03
    0.01
    250
    +0.03
    0.01
    Negative Logits
     Flavoring
    -0.26
    ITAL
    -0.23
    ollah
    -0.21
    Raven
    -0.21
    Ĥİ
    -0.21
     lamps
    -0.20
    Sov
    -0.19
    Mesh
    -0.19
    Reviewer
    -0.19
    lessly
    -0.19
    POSITIVE LOGITS
     chron
    0.21
    ocobo
    0.20
     Canadian
    0.19
    upload
    0.19
    coded
    0.19
    css
    0.19
    xual
    0.19
    /_
    0.19
    code
    0.19
    interpret
    0.18
    Activations Density 0.007%

    No Known Activations