© 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. 7-RES-JB
    11. 11720
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where someone is quick to respond or react to a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing promptness or swiftness in action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.66
    İĭ
    -0.65
    minus
    -0.65
    scope
    -0.64
    RAW
    -0.64
    cos
    -0.63
    ï¸
    -0.62
    ALLY
    -0.62
    IAL
    -0.61
     Fres
    -0.60
    POSITIVE LOGITS
     capitalize
    1.09
     criticize
    1.08
     seize
    1.06
     denounce
    1.02
     comply
    1.02
     adopt
    1.01
     proclaim
    1.01
     endorse
    1.00
     declare
    0.99
     respond
    0.99
    Activations Density 0.112%

    No Known Activations