© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7821
    Prev
    Next
    INDEX
    Explanations

    words related to evaluations or judgments, such as "assess" and "assessment."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evaluation and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icz
    -0.72
    corn
    -0.72
    feeding
    -0.72
    hold
    -0.69
    vous
    -0.67
    driver
    -0.64
    seed
    -0.63
    advertisement
    -0.62
    Else
    -0.62
    sil
    -0.62
    POSITIVE LOGITS
    itatively
    0.90
    oice
    0.82
    ments
    0.81
     assessing
    0.78
     assessment
    0.78
     assessments
    0.76
     probabilities
    0.73
     whether
    0.73
    mble
    0.73
    ively
    0.73
    Activations Density 0.041%

    No Known Activations