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. 7-RES-JB
    6. 4513
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement personnel or activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of law enforcement officials, particularly sheriffs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jad
    -0.82
    76561
    -0.77
    lihood
    -0.74
    ted
    -0.72
    ptions
    -0.69
    cing
    -0.69
    ced
    -0.68
    ername
    -0.67
     Centauri
    -0.65
    Austral
    -0.63
    POSITIVE LOGITS
     sheriff
    1.01
     Sheriff
    0.95
     deputies
    0.86
    osate
    0.84
     commissioner
    0.81
    Sher
    0.76
    alties
    0.76
     commissioners
    0.76
    icio
    0.76
     coroner
    0.75
    Activations Density 0.031%

    No Known Activations