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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 13374
    Prev
    Next
    INDEX
    Explanations

    references to violent acts and criminal incidents

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to crime and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (#
    -0.63
    Factor
    -0.62
    ist
    -0.61
     Minion
    -0.60
    osaurus
    -0.60
    dict
    -0.59
    ouble
    -0.58
    iel
    -0.57
    otally
    -0.55
    toc
    -0.55
    POSITIVE LOGITS
    agher
    0.92
    eating
    0.69
    rawdownloadcloneembedreportprint
    0.67
    swick
    0.66
    opian
    0.66
    Britain
    0.64
    accompan
    0.64
    mercial
    0.62
    England
    0.61
     Blackburn
    0.61
    Activations Density 0.128%

    No Known Activations