© 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. 11-RES-JB
    11. 22649
    Prev
    Next
    INDEX
    Explanations

    names of individuals with titles such as "Sir" and includes surnames

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals, particularly those with the title "Sir."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zona
    -0.75
    kamp
    -0.72
    erest
    -0.71
    tera
    -0.71
    cest
    -0.70
    nikov
    -0.66
    grounds
    -0.65
     stim
    -0.64
    ãĥł
    -0.64
    acia
    -0.64
    POSITIVE LOGITS
     Canterbury
    0.68
     Abbey
    0.67
     Browne
    0.65
     Hawkins
    0.65
     Thatcher
    0.64
     Cooke
    0.63
     Pradesh
    0.62
     Keynes
    0.62
     Cecil
    0.61
     Lawson
    0.60
    Activations Density 0.135%

    No Known Activations