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. 12261
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of people

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific characters or tokens

    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
     Cerberus
    -0.72
     Rebels
    -0.69
     Rebellion
    -0.65
     Skydragon
    -0.63
     captcha
    -0.63
     Leviathan
    -0.62
     dungeons
    -0.61
     hypoc
    -0.61
     pony
    -0.60
     ultras
    -0.58
    POSITIVE LOGITS
    ureen
    1.09
    berto
    1.06
    annie
    1.03
    jit
    1.03
    aryl
    1.03
    anya
    1.02
    ileen
    1.02
    ergus
    1.02
    ricia
    1.01
    resa
    1.01
    Activations Density 0.445%

    No Known Activations