© 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. 45808
    Prev
    Next
    INDEX
    Explanations

    phrases related to unexpected revelations or surprising discoveries

    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
    195
    +0.10
    0.5%
    319
    +0.10
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.10
    0.12
    84
    +0.10
    0.04
    640
    +0.10
    0.13
    Negative Logits
    ropolitan
    -0.65
     Colleg
    -0.61
    riot
    -0.61
    atana
    -0.60
    lain
    -0.60
    riots
    -0.59
    negie
    -0.58
    icipated
    -0.58
    è¦ļéĨĴ
    -0.57
    nea
    -0.56
    POSITIVE LOGITS
    ĸ
    0.64
    Ī
    0.64
     beet
    0.64
    terday
    0.63
    WT
    0.62
    pires
    0.59
     sour
    0.59
    Lua
    0.59
    PsyNetMessage
    0.58
    laus
    0.57
    Activations Density 4.185%

    No Known Activations