© 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. 7-RES-JB
    11. 20046
    Prev
    Next
    INDEX
    Explanations

    words with special characters like 'Ċ' and 'Ã'

    oai_token-act-pair · gpt-3.5-turbo

    discussions surrounding health insurance and medical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LF
    -0.67
     Samar
    -0.67
     Zig
    -0.67
     Oy
    -0.64
     Send
    -0.63
     Sal
    -0.63
     Syd
    -0.63
     Delicious
    -0.62
     Awesome
    -0.62
     Petro
    -0.62
    POSITIVE LOGITS
    within
    1.01
    without
    0.97
    alone
    0.95
    into
    0.93
    rem
    0.93
    and
    0.93
    against
    0.90
    rou
    0.90
    that
    0.88
    during
    0.86
    Activations Density 0.316%

    No Known Activations