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. 8-RES-JB
    6. 9383
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events taking place

    oai_token-act-pair · gpt-3.5-turbo

    actions or references to physical movement and separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cel
    -0.80
    jc
    -0.79
     Chili
    -0.79
    vine
    -0.79
    Comm
    -0.78
    glomer
    -0.78
     Cel
    -0.78
    Brit
    -0.74
    rencies
    -0.74
    ascal
    -0.74
    POSITIVE LOGITS
    out
    1.14
    OUT
    1.08
     outs
    1.06
     out
    1.06
     OUT
    1.04
     Out
    0.99
     Outs
    0.98
    outs
    0.95
     ay
    0.93
    Out
    0.88
    Activations Density 0.187%

    No Known Activations