© 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. 13735
    Prev
    Next
    INDEX
    Explanations

    the word "missed" coupled with various contexts, indicating a focus on events or actions that were not accomplished or experienced as expected

    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
    +0.22
    0.8%
    570
    +0.16
    0.6%
    491
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.22
    0.15
    491
    +0.16
    0.07
    362
    +0.14
    0.10
    Negative Logits
     Jinping
    -0.84
    gemony
    -0.82
    pour
    -0.80
    Reviewer
    -0.80
    escal
    -0.80
    ogue
    -0.78
    Technology
    -0.77
    PLA
    -0.76
    wcsstore
    -0.76
    xual
    -0.75
    POSITIVE LOGITS
    pelled
    1.26
    hap
    1.14
    pelling
    1.11
    poke
    1.07
    peak
    0.97
    pell
    0.97
    ouri
    0.93
    ordable
    0.92
     curfew
    0.91
     deadlines
    0.85
    Activations Density 8.187%

    No Known Activations