© 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 Local
    9. 6-RES_SCL-AJT
    11. 45757
    Prev
    Next
    INDEX
    Explanations

    HTTP-related terms and concepts such as HTTP requests, APIs, JSON, and server protocols

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.13
    0.8%
    385
    +0.09
    0.5%
    255
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.13
    0.07
    288
    +0.09
    0.16
    57
    +0.09
    0.05
    Negative Logits
    awatts
    -0.59
    Downloadha
    -0.58
    holder
    -0.56
    teen
    -0.53
    jad
    -0.53
    fman
    -0.52
    rolet
    -0.52
     Ukrain
    -0.51
    eca
    -0.51
    anu
    -0.51
    POSITIVE LOGITS
    ://
    0.74
    IME
    0.59
    ACK
    0.56
    TABLE
    0.56
    retty
    0.51
    ICAN
    0.51
    ãĤĭ
    0.50
    TPS
    0.50
     Digest
    0.50
    OST
    0.50
    Activations Density 6.049%

    No Known Activations