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. 4-RES-JB
    6. 21314
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement activities or equipment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of patrol-related activities or roles

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

    No Comments

    Negative Logits
    quickShipAvailable
    -0.82
    hur
    -0.82
    FORE
    -0.75
    urt
    -0.69
    akes
    -0.68
    ankind
    -0.66
    mort
    -0.66
    Wr
    -0.66
    iction
    -0.65
    omes
    -0.65
    POSITIVE LOGITS
     patrol
    1.19
     patrols
    1.13
     patrolling
    1.00
    andowski
    0.98
     Patrol
    0.98
     duty
    0.84
     officer
    0.82
     officers
    0.81
     trooper
    0.81
     personnel
    0.80
    Activations Density 0.010%

    No Known Activations