© 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. 40438
    Prev
    Next
    INDEX
    Explanations

    phrases related to adherence or commitment

    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
    365
    +0.18
    0.7%
    717
    +0.16
    0.6%
    41
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.25
    362
    +0.16
    0.14
    270
    +0.14
    0.07
    Negative Logits
    ellect
    -0.99
    apest
    -0.93
    ocaust
    -0.88
    odiac
    -0.87
    ģ«
    -0.85
    ELF
    -0.85
    ftime
    -0.84
    ·
    -0.83
    elf
    -0.83
    ®
    -0.81
    POSITIVE LOGITS
    itiveness
    0.95
    ciating
    0.90
     bounds
    0.86
     Puzzles
    0.85
     laure
    0.84
     plaster
    0.83
    shore
    0.81
    thin
    0.81
     sticks
    0.81
     Ashes
    0.79
    Activations Density 9.311%

    No Known Activations