© 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. 8-RES-JB
    11. 20328
    Prev
    Next
    INDEX
    Explanations

    mentions of congratulations or celebrations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Cong" and variations of it, typically related to organizations or awards

    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
     Gleaming
    -0.89
     Marketable
    -0.79
    pmwiki
    -0.77
    IPS
    -0.76
     SPORTS
    -0.72
    icist
    -0.70
     Leilan
    -0.68
     Witches
    -0.67
    istically
    -0.66
     Fields
    -0.66
    POSITIVE LOGITS
    regation
    1.17
    regate
    1.06
    rats
    1.06
    ression
    1.02
    cong
    0.97
    ressive
    0.94
    reg
    0.92
    resso
    0.91
    lishes
    0.91
    rat
    0.88
    Activations Density 0.036%

    No Known Activations