© 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. 16560
    Prev
    Next
    INDEX
    Explanations

    verbs related to growth, progress, or development

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to gaining popularity or acceptance

    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
    nia
    -0.74
    bey
    -0.71
     Audit
    -0.69
    dule
    -0.68
    aughty
    -0.68
     Emails
    -0.66
    zos
    -0.65
     Alone
    -0.64
    abies
    -0.64
    ounter
    -0.64
    POSITIVE LOGITS
     significance
    1.29
     prominence
    1.28
     urgency
    1.25
     relevance
    1.20
     impetus
    1.17
     traction
    1.16
     importance
    1.16
     momentum
    1.14
     resonance
    1.11
     vitality
    1.11
    Activations Density 0.227%

    No Known Activations