© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 33079
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals with the title 'Lady'

    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
    +0.16
    0.8%
    326
    +0.11
    0.6%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.16
    0.23
    504
    +0.11
    0.07
    161
    +0.10
    0.04
    Negative Logits
    CAST
    -0.64
    onential
    -0.62
    aeda
    -0.60
    icted
    -0.60
    obyl
    -0.60
    osta
    -0.59
    ozy
    -0.59
    insula
    -0.59
    66666666
    -0.59
    venants
    -0.57
    POSITIVE LOGITS
     Gaga
    1.21
    bug
    1.06
    bird
    1.05
    bugs
    0.91
    birds
    0.86
    maid
    0.81
    ng
    0.76
    weed
    0.76
     Jane
    0.75
     Mary
    0.74
    Activations Density 11.571%

    No Known Activations