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. 6-RES-JB
    6. 16440
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement, specifically the position of sheriff

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement officials, specifically sheriffs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.83
    lihood
    -0.82
    jad
    -0.82
    ted
    -0.77
    ptions
    -0.70
    ced
    -0.69
    ername
    -0.66
    uve
    -0.66
    pace
    -0.66
    xual
    -0.66
    POSITIVE LOGITS
     sheriff
    1.01
     Sheriff
    0.99
    osate
    0.88
     commissioner
    0.79
     deputies
    0.78
    icio
    0.76
    uty
    0.75
     coroner
    0.75
     Arpaio
    0.74
    Sher
    0.74
    Activations Density 0.019%

    No Known Activations