© 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. 45889
    Prev
    Next
    INDEX
    Explanations

    terms related to programming concepts and software development

    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
    218
    +0.13
    0.6%
    447
    +0.12
    0.5%
    153
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    738
    +0.13
    0.08
    67
    +0.12
    0.19
    316
    +0.11
    0.11
    Negative Logits
     ·
    -0.73
    Reviewer
    -0.70
     âĵĺ
    -0.67
    soDeliveryDate
    -0.65
     sclerosis
    -0.62
     Emin
    -0.62
     âĢº
    -0.62
     Clover
    -0.61
     Homo
    -0.57
     Dahl
    -0.55
    POSITIVE LOGITS
    frac
    0.79
    ifice
    0.78
    escription
    0.74
    netflix
    0.74
    omever
    0.72
    iterranean
    0.66
    adish
    0.65
    fty
    0.64
    FFFF
    0.64
    ablishment
    0.63
    Activations Density 24.252%

    No Known Activations