© 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. 32271
    Prev
    Next
    INDEX
    Explanations

    instances where someone is being informed or directed to take specific actions

    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
    +0.31
    1.8%
    679
    +0.09
    0.5%
    665
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.31
    0.18
    460
    +0.09
    0.08
    10
    +0.08
    0.07
    Negative Logits
    ivot
    -0.54
    adesh
    -0.52
    rouse
    -0.51
    Labor
    -0.50
    ADD
    -0.49
    aho
    -0.48
    vous
    -0.48
     Confeder
    -0.47
    aband
    -0.47
    hur
    -0.47
    POSITIVE LOGITS
     by
    0.60
     orally
    0.56
    terday
    0.55
     repeatedly
    0.55
    tale
    0.53
     permission
    0.53
    ļé
    0.52
    ews
    0.51
     briefings
    0.50
    ĨĴ
    0.49
    Activations Density 8.767%

    No Known Activations