© 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. 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. 1196
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "bass", particularly in relation to music

    oai_token-act-pair · gpt-3.5-turbo

    references to bass instruments in music

    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
     Expend
    -0.75
     Reincarn
    -0.68
    ATIONAL
    -0.67
    gur
    -0.65
     Hubble
    -0.62
     Volunte
    -0.62
     Leone
    -0.60
     Lann
    -0.59
     Bayer
    -0.59
     Britann
    -0.59
    POSITIVE LOGITS
    nect
    1.45
    istics
    1.13
    inet
    1.07
    holes
    1.03
    line
    0.95
    lines
    0.93
    liner
    0.92
    ette
    0.91
     guitar
    0.90
    etry
    0.89
    Activations Density 0.025%

    No Known Activations