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. 6756
    Prev
    Next
    INDEX
    Explanations

    violence-related phrases involving physical harm and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents or fatalities

    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
    retty
    -0.55
    awaru
    -0.52
    udos
    -0.51
     Vaugh
    -0.50
     conclud
    -0.50
    soDeliveryDate
    -0.49
     incorpor
    -0.49
     furthermore
    -0.49
     however
    -0.48
     moreover
    -0.48
    POSITIVE LOGITS
    )?
    0.64
    ?",
    0.59
     \'
    0.53
    apor
    0.52
     ])
    0.52
    )|
    0.51
    Ħ¢
    0.50
    )]
    0.49
    their
    0.49
    ?),
    0.49
    Activations Density 2.041%

    No Known Activations