© 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. 34835
    Prev
    Next
    INDEX
    Explanations

    activities or tasks that have been successfully carried out or accomplished

    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
    +0.30
    1.4%
    59
    +0.13
    0.6%
    207
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.30
    0.24
    746
    +0.13
    0.01
    665
    +0.11
    0.13
    Negative Logits
    maid
    -0.70
    gypt
    -0.65
    lua
    -0.64
    spr
    -0.64
    brow
    -0.60
    bour
    -0.59
    hot
    -0.58
    ung
    -0.57
    iewicz
    -0.57
    tem
    -0.56
    POSITIVE LOGITS
    issance
    0.87
    teness
    0.81
    TAIN
    0.81
    ances
    0.79
     completion
    0.72
     srf
    0.70
     feasibility
    0.70
     captcha
    0.67
    uberty
    0.66
     preparations
    0.65
    Activations Density 11.425%

    No Known Activations