© 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. 10-RES-JB
    11. 24516
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals with a similar suffix, likely a Russian or Eastern European origin

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of names or surnames, particularly those of individuals from Eastern Europe or Russia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tasman
    -0.71
    Walker
    -0.69
     UNC
    -0.67
     Ellison
    -0.67
    FACE
    -0.66
     Catalyst
    -0.66
     Whitman
    -0.62
     Loll
    -0.62
     runners
    -0.62
    comb
    -0.62
    POSITIVE LOGITS
    ski
    1.79
    sky
    1.58
    sk
    1.28
    itch
    1.24
    achev
    1.19
    nikov
    1.18
    itz
    1.12
    icz
    1.09
    kaya
    1.05
    ny
    1.03
    Activations Density 0.084%

    No Known Activations