© 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. 10-RES-JB
    11. 2693
    Prev
    Next
    INDEX
    Explanations

    words related to historical context or events

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with historical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nery
    -0.86
    lain
    -0.82
    ertodd
    -0.77
    Flow
    -0.77
    Downloadha
    -0.76
    DAQ
    -0.73
    Kids
    -0.72
    geon
    -0.71
    rosis
    -0.70
    aye
    -0.68
    POSITIVE LOGITS
     significance
    0.99
    orical
    0.98
    orically
    0.95
     precedent
    0.94
     preservation
    0.93
     revision
    0.87
     preced
    0.86
     landmarks
    0.83
     relics
    0.80
     proportions
    0.79
    Activations Density 0.048%

    No Known Activations