© 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. 23795
    Prev
    Next
    INDEX
    Explanations

    capitalized abbreviations and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    acronyms, abbreviations, and technical terms

    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
    ways
    -0.72
     seiz
    -0.69
    ¥µ
    -0.63
    enhagen
    -0.60
    PsyNetMessage
    -0.60
     plur
    -0.59
    Duration
    -0.58
     metic
    -0.57
    azeera
    -0.56
     attrition
    -0.56
    POSITIVE LOGITS
    asus
    0.84
    Äĩ
    0.76
    umatic
    0.73
    ongyang
    0.72
    Cola
    0.72
    ciation
    0.72
    γ
    0.71
    zza
    0.71
    lator
    0.70
    formance
    0.69
    Activations Density 0.412%

    No Known Activations