© 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. 34959
    Prev
    Next
    INDEX
    Explanations

    words related to news events and incidents

    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
    679
    +0.11
    0.6%
    739
    +0.10
    0.5%
    50
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.11
    0.10
    698
    +0.10
    0.04
    748
    +0.09
    0.02
    Negative Logits
    uality
    -0.69
    agate
    -0.65
    ually
    -0.62
     Galile
    -0.60
    ife
    -0.60
     bald
    -0.59
    ,,,,
    -0.55
     chang
    -0.53
     nib
    -0.53
     vision
    -0.52
    POSITIVE LOGITS
    ustration
    0.67
    advertisement
    0.66
    giving
    0.66
     Continue
    0.66
    Enlarge
    0.65
     Emails
    0.65
     Videos
    0.65
    taboola
    0.64
     Credits
    0.64
     Thumbnails
    0.62
    Activations Density 4.052%

    No Known Activations