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. 8-RES-JB
    6. 8771
    Prev
    Next
    INDEX
    Explanations

    legal or rule-related terms, and also potential threats or offenses

    oai_token-act-pair · gpt-3.5-turbo

    instances of formal declarations or legal terminology

    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
    ilogy
    -0.68
     Paddock
    -0.65
    enture
    -0.64
    ciples
    -0.64
     Palmer
    -0.63
    knit
    -0.62
     figure
    -0.61
    anchester
    -0.60
    utherland
    -0.60
    ocket
    -0.59
    POSITIVE LOGITS
     dishon
    0.96
     unacceptable
    0.95
     unworthy
    0.86
     fail
    0.86
    Invalid
    0.86
     disgrace
    0.85
    Failure
    0.85
     discredit
    0.83
     unfit
    0.83
     failure
    0.82
    Activations Density 0.759%

    No Known Activations