© 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. 3-RES-JB
    11. 23170
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and specific governmental bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to educational inspections and organizations involved in school oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mathemat
    -0.92
     confir
    -0.86
     simultane
    -0.82
    ĺħ
    -0.82
     exha
    -0.79
     cumbers
    -0.73
     traged
    -0.72
     reluct
    -0.71
     actu
    -0.70
     attendant
    -0.70
    POSITIVE LOGITS
    cot
    1.18
    arget
    1.16
    chio
    1.09
    otle
    1.03
    rans
    0.97
    hew
    0.92
    ting
    0.91
    agon
    0.91
    olkien
    0.90
    pole
    0.90
    Activations Density 0.015%

    No Known Activations