© 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. 4384
    Prev
    Next
    INDEX
    Explanations

    technical information and discussions related to software, hardware, and technological features

    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
    18
    +0.13
    0.6%
    76
    +0.11
    0.5%
    512
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.13
    0.13
    430
    +0.11
    0.19
    649
    +0.10
    0.06
    Negative Logits
    chio
    -0.78
    akespe
    -0.71
    bledon
    -0.70
    hetti
    -0.69
     sabot
    -0.68
     comr
    -0.67
    ploma
    -0.66
    ModLoader
    -0.66
    iaries
    -0.66
    bage
    -0.66
    POSITIVE LOGITS
     08
    0.82
    th
    0.77
     07
    0.76
     09
    0.75
    arth
    0.73
     05
    0.73
    TH
    0.72
     02
    0.72
     04
    0.71
    2200
    0.71
    Activations Density 9.665%

    No Known Activations