© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2653
    Prev
    Next
    INDEX
    Explanations

    information related to data management or updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the status and management of characters or accounts in a gaming or online context

    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
     clich
    -0.78
     tangled
    -0.76
     tract
    -0.72
     caricature
    -0.70
     Witt
    -0.70
     Laden
    -0.70
    aq
    -0.70
    gall
    -0.70
    ghazi
    -0.69
     embarrass
    -0.69
    POSITIVE LOGITS
     refunds
    1.14
     Updates
    1.13
     Login
    1.07
     Users
    1.07
     Customers
    1.06
     notification
    0.95
     updates
    0.95
     Notification
    0.95
     Rewards
    0.91
     Previously
    0.91
    Activations Density 0.862%

    No Known Activations