© 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. 46026
    Prev
    Next
    INDEX
    Explanations

    questions in a dialogue

    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
    50
    +0.15
    0.6%
    572
    +0.12
    0.5%
    357
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.15
    0.15
    338
    +0.12
    0.12
    640
    +0.11
    0.20
    Negative Logits
    ĸļ
    -0.88
    è¦ļéĨĴ
    -0.84
    ripp
    -0.77
    resses
    -0.75
    abies
    -0.75
    arette
    -0.73
    ernel
    -0.73
    ulator
    -0.72
    inational
    -0.72
     neglig
    -0.72
    POSITIVE LOGITS
    eous
    1.56
    ward
    0.85
     fielder
    0.83
    move
    0.82
     wing
    0.81
     winger
    0.78
    wing
    0.78
     Stuff
    0.77
    lander
    0.76
     Wing
    0.75
    Activations Density 5.984%

    No Known Activations