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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 35006
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the source of information or analysis

    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
    +0.26
    1.4%
    393
    +0.13
    0.7%
    235
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.26
    0.30
    362
    +0.13
    0.16
    640
    +0.10
    0.26
    Negative Logits
    ©¶æ¥µ
    -0.71
    vous
    -0.66
    Forge
    -0.65
    seek
    -0.60
    bats
    -0.56
    Palest
    -0.56
    arat
    -0.55
    apers
    -0.55
    zon
    -0.55
    associated
    -0.54
    POSITIVE LOGITS
     behalf
    0.80
     assumption
    0.67
     principles
    0.67
     principle
    0.63
     sheer
    0.62
     hears
    0.59
     Demand
    0.59
     demand
    0.58
     scraps
    0.58
     suspicion
    0.58
    Activations Density 13.350%

    No Known Activations