© 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. 4303
    Prev
    Next
    INDEX
    Explanations

    phrases related to prevention or prohibition

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing prevention or obstruction

    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
    bush
    -0.74
    aic
    -0.71
    soDeliveryDate
    -0.69
    quickShipAvailable
    -0.69
    uid
    -0.67
    rote
    -0.67
    artisan
    -0.65
    geist
    -0.65
    hen
    -0.65
    worker
    -0.65
    POSITIVE LOGITS
     accessing
    1.14
     reaching
    1.06
     completing
    1.01
     obtaining
    0.99
     being
    0.98
     entering
    0.95
     becoming
    0.94
     achieving
    0.93
     joining
    0.92
     owning
    0.91
    Activations Density 0.080%

    No Known Activations