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. 8654
    Prev
    Next
    INDEX
    Explanations

    phrases related to off-duty police officers or military personnel

    oai_token-act-pair · gpt-3.5-turbo

    references to police duty and related terms

    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
     breakout
    -0.72
     clone
    -0.72
     orphan
    -0.69
     cat
    -0.68
     mentioned
    -0.66
     score
    -0.64
     transition
    -0.64
     rapidly
    -0.63
     dominate
    -0.63
     Pirate
    -0.62
    POSITIVE LOGITS
    duty
    4.24
     Duty
    1.82
     duty
    1.25
    uty
    1.20
    toe
    1.01
    strength
    1.01
    combat
    0.99
    police
    0.98
    lift
    0.97
    tenance
    0.95
    Activations Density 0.021%

    No Known Activations