© 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. 11-RES-JB
    11. 19330
    Prev
    Next
    INDEX
    Explanations

    calls to action or invitations to join a group or project

    oai_token-act-pair · gpt-3.5-turbo

    positive phrases encouraging participation and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gypt
    -0.73
    inventoryQuantity
    -0.71
    RECT
    -0.69
     overc
    -0.68
    tesque
    -0.68
     Sears
    -0.68
     restraint
    -0.68
     Bundy
    -0.66
    quickShipAvailable
    -0.66
     reversal
    -0.66
    POSITIVE LOGITS
     Volunte
    1.35
     Telegram
    1.34
     Discord
    1.27
     Membership
    1.27
     IRC
    1.26
     Volunteer
    1.24
     volunteering
    1.15
     Join
    1.13
     volunteer
    1.12
     Registration
    1.12
    Activations Density 0.447%

    No Known Activations