© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7588
    Prev
    Next
    INDEX
    Explanations

    terms related to ongoing or continuing activities or situations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with persistent situations or conditions

    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
    »Ĵ
    -0.78
    eah
    -0.76
    enton
    -0.72
    esar
    -0.72
    ertodd
    -0.71
    icans
    -0.70
    uddenly
    -0.69
    estamp
    -0.68
    erved
    -0.68
    Always
    -0.67
    POSITIVE LOGITS
     hostilities
    1.01
     saga
    0.99
     investigation
    0.98
     effort
    0.98
     efforts
    0.96
     struggle
    0.95
     fascination
    0.92
     investigations
    0.89
     litigation
    0.89
     controversy
    0.89
    Activations Density 0.067%

    No Known Activations