© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36450
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to top or high priorities and designations

    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
    +0.27
    1.2%
    288
    +0.13
    0.6%
    737
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.27
    0.38
    608
    +0.13
    0.24
    703
    +0.13
    0.12
    Negative Logits
    ocks
    -0.77
    inally
    -0.76
    tiny
    -0.76
    reens
    -0.74
    ears
    -0.74
    ingers
    -0.74
    sk
    -0.73
    imar
    -0.72
    rawling
    -0.72
    avery
    -0.71
    POSITIVE LOGITS
     priority
    0.98
     duty
    0.93
     priorities
    0.92
     consideration
    0.91
     prioritize
    0.89
     priorit
    0.87
    priority
    0.84
     allocation
    0.84
     Priority
    0.81
     allocations
    0.74
    Activations Density 16.286%

    No Known Activations