© 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. 6357
    Prev
    Next
    INDEX
    Explanations

    verbs that have the suffix "-vin" in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "vin" in various contexts

    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
     Seym
    -0.85
    arers
    -0.72
    lain
    -0.70
    deen
    -0.68
    ngth
    -0.68
    ropolitan
    -0.67
    riz
    -0.66
    ossal
    -0.65
    awaru
    -0.63
    retched
    -0.62
    POSITIVE LOGITS
    eland
    0.90
    istic
    0.90
    ces
    0.87
    icum
    0.85
    istically
    0.83
    icio
    0.82
    eteen
    0.82
    jury
    0.81
    itive
    0.81
    osaurs
    0.80
    Activations Density 0.059%

    No Known Activations