Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9102
    Prev
    Next
    INDEX
    Explanations

    terms related to key strategic positions and vital resources

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to strategic importance and critical resources

    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
    otti
    -0.76
    osa
    -0.71
    igham
    -0.71
     Wonderland
    -0.69
    ritch
    -0.68
     Carbuncle
    -0.66
    ateurs
    -0.63
     broom
    -0.63
     vomiting
    -0.62
    acci
    -0.62
    POSITIVE LOGITS
     viz
    0.94
     namely
    0.69
     (>
    0.67
    stone
    0.66
     jun
    0.63
     discoveries
    0.62
    rients
    0.62
     artery
    0.62
     affecting
    0.61
    atform
    0.61
    Activations Density 0.301%

    No Known Activations