© 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 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. 33039
    Prev
    Next
    INDEX
    Explanations

    time-related references and sequences

    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
    393
    +0.10
    0.6%
    447
    +0.10
    0.6%
    59
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.26
    210
    +0.10
    0.07
    283
    +0.09
    0.01
    Negative Logits
    ENG
    -0.66
    Offline
    -0.59
    Lenin
    -0.53
    Hen
    -0.53
    VIDEO
    -0.51
    ISM
    -0.50
    advertisement
    -0.50
    aren
    -0.49
    assy
    -0.49
    à¨
    -0.48
    POSITIVE LOGITS
     anyone
    0.60
     returning
    0.53
     enroll
    0.52
     anybody
    0.52
     retiring
    0.50
     succ
    0.49
     sunset
    0.49
     settling
    0.49
     sunrise
    0.49
     disqual
    0.48
    Activations Density 11.023%

    No Known Activations