© 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. 15780
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the surname 'Fisher.'

    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
    ivity
    -0.78
    ifiable
    -0.75
    ifier
    -0.74
    ional
    -0.68
    ifying
    -0.66
    LCS
    -0.65
    ifies
    -0.64
    ULAR
    -0.63
    ified
    -0.63
    places
    -0.62
    POSITIVE LOGITS
    hoff
    0.84
     Coliseum
    0.84
    gaard
    0.69
    enegger
    0.69
     AFB
    0.69
    hurst
    0.68
    gren
    0.68
    mania
    0.67
     Humph
    0.66
    batch
    0.66
    Activations Density 0.128%

    No Known Activations