© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 14179
    Prev
    Next
    INDEX
    Explanations

    references to news publications or media outlets

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "inquire" and its variations

    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
     diam
    -0.64
     NCT
    -0.61
     vein
    -0.61
     tamp
    -0.58
     deterrence
    -0.58
     tread
    -0.57
    paper
    -0.57
    isin
    -0.55
     separ
    -0.54
    timer
    -0.54
    POSITIVE LOGITS
    ÙĦ
    0.83
    ean
    0.82
    arthed
    0.73
    sbm
    0.73
    advertisement
    0.71
    ©
    0.71
    د
    0.70
    hner
    0.70
    ģ
    0.69
    Flickr
    0.68
    Activations Density 0.103%

    No Known Activations