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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 35436
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions of events from various situations

    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
    481
    +0.16
    0.9%
    215
    +0.07
    0.5%
    364
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.16
    -0.06
    762
    +0.07
    0.21
    570
    +0.07
    -0.00
    Negative Logits
     argues
    -0.66
     regimes
    -0.55
     contends
    -0.54
     asserts
    -0.53
    ths
    -0.53
     cite
    -0.53
     Historically
    -0.52
     rhet
    -0.52
     advocates
    -0.51
     acknowledges
    -0.50
    POSITIVE LOGITS
    —"
    0.58
     prank
    0.57
    orage
    0.53
    apest
    0.53
     alright
    0.52
    netflix
    0.51
     supper
    0.49
     trespass
    0.49
    yip
    0.48
     smell
    0.48
    Activations Density 13.386%

    No Known Activations