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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22244
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology or cybersecurity, specifically mentioning experts or certain technologies

    oai_token-act-pair · gpt-3.5-turbo

    words related to cyber security or technology-related scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uterte
    -0.71
     caricature
    -0.69
     blunt
    -0.69
     stereotypical
    -0.68
     mock
    -0.65
     cul
    -0.64
     reader
    -0.64
     aggrav
    -0.64
    igate
    -0.63
     exotic
    -0.62
    POSITIVE LOGITS
    sle
    0.83
    FTWARE
    0.81
    overed
    0.75
    REF
    0.74
    æł
    0.72
    GM
    0.72
    rolet
    0.70
    ================================================================
    0.69
    ":"/
    0.69
    æŃ
    0.69
    Activations Density 0.000%

    No Known Activations