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

    Neuronpedia

    APICircuit 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. 67
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, particularly related to political figures or locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hof."

    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
     Rebirth
    -0.70
     Curse
    -0.68
     Minimum
    -0.65
    Minimum
    -0.64
     Marvel
    -0.64
     Origin
    -0.63
     Garry
    -0.63
     Cosmic
    -0.62
     codes
    -0.61
     Symb
    -0.61
    POSITIVE LOGITS
    hof
    4.11
    hoff
    1.90
    merga
    1.64
     Stras
    1.54
    wagen
    1.34
    Aid
    1.21
     Yaz
    1.17
    gang
    1.17
    steen
    1.15
    minster
    1.11
    Activations Density 0.040%

    No Known Activations