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. 0-RES-JB
    6. 3561
    Prev
    Next
    INDEX
    Explanations

    names or titles related to law enforcement personnel

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Sheriff."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vi
    -0.67
    anges
    -0.65
    jing
    -0.64
     favourable
    -0.63
     uncom
    -0.63
    cube
    -0.63
     tubes
    -0.61
    aments
    -0.60
    ø
    -0.60
    opic
    -0.59
    POSITIVE LOGITS
     Sheriff
    3.60
     sheriff
    3.06
    Sher
    1.93
     sher
    1.79
     Arpaio
    1.78
     coroner
    1.60
     deputies
    1.57
    paio
    1.54
     Jail
    1.49
     Prosecutor
    1.43
    Activations Density 0.017%

    No Known Activations