© 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. 8-RES-JB
    11. 2242
    Prev
    Next
    INDEX
    Explanations

    references to the human body and physical characteristics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological and physiological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rosso
    -0.80
    issions
    -0.74
     Niet
    -0.74
    catentry
    -0.72
    ALSE
    -0.70
    Anth
    -0.70
    iev
    -0.68
    ults
    -0.68
    renheit
    -0.67
    results
    -0.67
    POSITIVE LOGITS
     indispensable
    0.99
     metaphor
    0.94
     sacred
    0.91
     inherently
    0.88
     ALWAYS
    0.88
     interchangeable
    0.86
     intrinsically
    0.85
     precious
    0.84
     uniquely
    0.84
     totem
    0.82
    Activations Density 0.706%

    No Known Activations