© 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. 34737
    Prev
    Next
    INDEX
    Explanations

    numbers with a specific format like decimals, IP addresses, and codes

    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
    480
    +0.02
    0.5%
    593
    +0.02
    0.5%
    103
    +0.02
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.02
    0.50
    640
    +0.02
    0.46
    745
    +0.02
    -0.24
    Negative Logits
    osponsors
    -0.19
    uous
    -0.13
    ité
    -0.13
     reps
    -0.12
    rr
    -0.12
    racuse
    -0.11
     lobb
    -0.11
    ú
    -0.11
    ades
    -0.11
    nce
    -0.11
    POSITIVE LOGITS
    Weather
    0.14
    Chip
    0.14
    Template
    0.14
    Icon
    0.13
    Spread
    0.13
    RFC
    0.13
    Getty
    0.13
    Gas
    0.13
    Thumbnail
    0.13
    DragonMagazine
    0.13
    Activations Density 24.574%

    No Known Activations