© 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. 13642
    Prev
    Next
    INDEX
    Explanations

    mentions of technology-related terms, particularly related to user commands, software development, and internet devices

    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
    +0.22
    1.0%
    414
    +0.10
    0.5%
    674
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.22
    0.13
    70
    +0.10
    0.14
    184
    +0.10
    0.04
    Negative Logits
    wx
    -0.77
    yssey
    -0.76
     Detail
    -0.72
    ©¶æ¥µ
    -0.71
    imity
    -0.69
    ruciating
    -0.68
    accompanied
    -0.65
    iferation
    -0.64
    NetMessage
    -0.64
    geoning
    -0.63
    POSITIVE LOGITS
    ?:
    1.27
    ?).
    1.25
    ?)
    1.22
    ?),
    1.19
    ?
    1.19
    ?'
    1.16
    ?",
    1.12
    ?".
    1.11
    ?"
    1.09
    ...?
    1.06
    Activations Density 17.913%

    No Known Activations