© 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. 4129
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experience and opinion.

    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
    +0.17
    0.9%
    502
    +0.11
    0.6%
    167
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.17
    0.14
    718
    +0.11
    0.17
    502
    +0.10
    0.09
    Negative Logits
     Nora
    -0.56
     Uriel
    -0.53
     Dickinson
    -0.51
     DeVos
    -0.51
     goodbye
    -0.51
     abdom
    -0.50
     Gale
    -0.50
    heres
    -0.49
    edient
    -0.49
     Mats
    -0.47
    POSITIVE LOGITS
    'm
    1.01
    've
    0.88
     am
    0.77
    RL
    0.74
    pec
    0.73
     suppose
    0.73
     wish
    0.72
     myself
    0.72
    UC
    0.70
    stad
    0.70
    Activations Density 11.214%

    No Known Activations