© 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. 1-RES-JB
    11. 16865
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named "Cotto" and related actions or events involving this person

    oai_token-act-pair · gpt-3.5-turbo

    the name "Cotto" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mental
    -0.72
    dry
    -0.66
    eric
    -0.66
    demand
    -0.65
    meet
    -0.63
    ships
    -0.62
    drawn
    -0.62
    effic
    -0.61
     capitals
    -0.61
    shr
    -0.61
    POSITIVE LOGITS
    otto
    1.29
    veyard
    0.89
    ertodd
    0.73
    iddler
    0.73
    acher
    0.73
    iful
    0.73
    ansky
    0.70
    tsky
    0.70
    urnal
    0.69
    annis
    0.68
    Activations Density 0.009%

    No Known Activations