© 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. 4075
    Prev
    Next
    INDEX
    Explanations

    terms related to genetics and genomic research

    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
    575
    +0.07
    0.6%
    651
    +0.07
    0.5%
    160
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.07
    0.20
    651
    +0.07
    0.11
    575
    +0.06
    0.14
    Negative Logits
    ornia
    -0.48
    ressive
    -0.47
    enhagen
    -0.43
    uay
    -0.42
    GF
    -0.41
    ħĭ
    -0.41
    withstanding
    -0.41
    lasses
    -0.40
    gotten
    -0.40
     Yel
    -0.40
    POSITIVE LOGITS
     genome
    0.46
    arium
    0.46
     sequencing
    0.46
     biologist
    0.43
     Foss
    0.42
     genomes
    0.41
    zyme
    0.40
    ortex
    0.40
    ographer
    0.39
     Browser
    0.39
    Activations Density 6.370%

    No Known Activations