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. 0-RES-JB
    6. 23599
    Prev
    Next
    INDEX
    Explanations

    names and terms related to legal or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly a person named Norris

    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
    RAM
    -0.74
    Bey
    -0.71
    ADVERTISEMENT
    -0.70
     Dalai
    -0.69
     bead
    -0.68
     Latest
    -0.65
     Tablet
    -0.64
    apest
    -0.62
    Gb
    -0.62
    crop
    -0.61
    POSITIVE LOGITS
     Norris
    2.45
    atus
    1.97
     conce
    1.17
    agin
    1.05
     CONT
    1.03
     strang
    0.94
    eki
    0.91
     Willis
    0.90
    atham
    0.88
     forwards
    0.86
    Activations Density 0.046%

    No Known Activations