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. 10-RES-JB
    6. 18405
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals with the last name "Bar" followed by various endings such as "ro", "ak", "ric", "gh", "zil", "uc", "ber"

    oai_token-act-pair · gpt-3.5-turbo

    references to names and terms associated with prominent individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.70
    advertisement
    -0.58
     Remastered
    -0.57
    ritch
    -0.55
     Mormonism
    -0.55
    apache
    -0.55
     compe
    -0.54
     paralle
    -0.54
    æĢ
    -0.52
     exert
    -0.52
    POSITIVE LOGITS
    aroo
    1.02
    anamo
    0.80
    hani
    0.77
    ulla
    0.76
    enture
    0.75
    ã
    0.72
    owitz
    0.69
    zona
    0.68
    uese
    0.68
    oux
    0.68
    Activations Density 0.090%

    No Known Activations