© 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. 35787
    Prev
    Next
    INDEX
    Explanations

    specific names of sports teams or locations

    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
    +0.48
    2.6%
    169
    +0.09
    0.5%
    326
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.48
    0.14
    527
    +0.09
    0.07
    169
    +0.09
    0.15
    Negative Logits
    uminati
    -0.62
     sqor
    -0.61
    igslist
    -0.57
    advertisement
    -0.55
    interstitial
    -0.55
    è¦ļéĨĴ
    -0.54
    tones
    -0.53
    ;;;;;;;;;;;;
    -0.53
    ãĥĩãĤ£
    -0.53
    ,,,,,,,,
    -0.53
    POSITIVE LOGITS
    's
    0.78
     lacks
    0.75
     could
    0.73
     forgot
    0.73
     did
    0.70
     excel
    0.68
     lacked
    0.68
     cannot
    0.67
     itself
    0.67
     hadn
    0.67
    Activations Density 13.104%

    No Known Activations