© 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. 9-RES-JB
    11. 17530
    Prev
    Next
    INDEX
    Explanations

    terms related to recommending or proposing actions or ideas

    oai_token-act-pair · gpt-3.5-turbo

    expressions of recommendations or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gie
    -0.89
    pes
    -0.75
    FO
    -0.74
    mb
    -0.73
    fare
    -0.73
    kai
    -0.72
    cedented
    -0.72
    otype
    -0.71
    tt
    -0.70
    percent
    -0.69
    POSITIVE LOGITS
     otherwise
    0.91
    ively
    0.80
     that
    0.73
     alternatives
    0.71
     remedies
    0.69
     avenues
    0.69
     reconsider
    0.67
     caution
    0.67
     alternative
    0.65
     anew
    0.65
    Activations Density 0.060%

    No Known Activations