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. 0-RES-JB
    6. 19460
    Prev
    Next
    INDEX
    Explanations

    words related to fugitives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fugitives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynski
    -0.74
    acca
    -0.68
    heimer
    -0.66
    store
    -0.65
    cards
    -0.65
    child
    -0.63
    ord
    -0.63
    uster
    -0.63
    eson
    -0.63
    rian
    -0.62
    POSITIVE LOGITS
    netflix
    0.78
    yip
    0.76
    entin
    0.70
     iceberg
    0.67
    ailability
    0.67
     Niet
    0.67
    jri
    0.66
    comings
    0.66
     Ãľ
    0.66
     enthusi
    0.63
    Activations Density 0.000%

    No Known Activations