© 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. 1-RES-JB
    11. 14487
    Prev
    Next
    INDEX
    Explanations

    SSH (Secure Shell) related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical significance in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ç¥ŀ
    -0.73
    ãĥ£
    -0.69
    lessly
    -0.68
    Äĩ
    -0.67
     Hurricanes
    -0.64
    isha
    -0.63
     POLITICO
    -0.63
     Gamble
    -0.62
     Lions
    -0.61
     bankruptcy
    -0.61
    POSITIVE LOGITS
    SS
    1.36
    LT
    0.91
    LP
    0.89
    RM
    0.88
    BM
    0.88
    APD
    0.88
    AA
    0.87
    HT
    0.87
    gt
    0.85
    DK
    0.85
    Activations Density 0.004%

    No Known Activations