Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7868
    Prev
    Next
    INDEX
    Explanations

    informal expressions or interjections

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.99
    iband
    -0.81
    ividual
    -0.76
    rift
    -0.75
    sbm
    -0.74
    Ĥİ
    -0.74
    icipated
    -0.73
    hyde
    -0.72
    ussia
    -0.70
    erguson
    -0.69
    POSITIVE LOGITS
     kidding
    1.33
     huh
    1.09
    Huh
    1.09
     Oops
    1.04
    Sounds
    1.01
     irony
    0.99
    ?!
    0.98
     Hmm
    0.96
     ironic
    0.92
    Seriously
    0.92
    Activations Density 0.439%

    No Known Activations