© 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. 695
    Prev
    Next
    INDEX
    Explanations

    specific dates and events

    oai_token-act-pair · gpt-3.5-turbo

    significant events or milestones

    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
     endif
    -0.74
    ichever
    -0.71
     unspecified
    -0.70
     upkeep
    -0.68
     sclerosis
    -0.67
     future
    -0.67
     occasional
    -0.65
     periodic
    -0.64
     sequels
    -0.64
     disputes
    -0.64
    POSITIVE LOGITS
     yesterday
    1.17
     ðŁ
    1.03
     ðŁij
    0.98
    ðŁ
    0.98
     Yesterday
    0.93
    âľ
    0.92
    ãĢ
    0.90
     Congratulations
    0.90
    Yesterday
    0.90
    ðŁij
    0.90
    Activations Density 0.743%

    No Known Activations