Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45187
    Prev
    Next
    INDEX
    Explanations

    code structures and technical terms found in programming

    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
    59
    +0.12
    0.6%
    311
    +0.11
    0.5%
    651
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.17
    507
    +0.11
    0.10
    326
    +0.11
    0.18
    Negative Logits
     Clarkson
    -0.66
     Ferry
    -0.65
     Wynne
    -0.64
     curfew
    -0.63
     DOE
    -0.62
    cale
    -0.61
     Giles
    -0.59
    peed
    -0.59
     overboard
    -0.58
     clutch
    -0.58
    POSITIVE LOGITS
    urally
    1.48
    uring
    1.21
    ured
    1.17
    urer
    1.09
    uration
    1.02
    rait
    1.01
    ript
    0.97
    ures
    0.97
    urers
    0.95
    ural
    0.94
    Activations Density 6.374%

    No Known Activations