Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 19130
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement or police activity, especially focusing on off-duty scenarios

    oai_token-act-pair · gpt-3.5-turbo

    references to police officers on duty or off-duty contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Juliet
    -0.84
     Rosenthal
    -0.76
    hematic
    -0.74
    anz
    -0.74
     Tate
    -0.73
    vae
    -0.72
    ergy
    -0.71
    iques
    -0.68
     TED
    -0.67
     Ridley
    -0.66
    POSITIVE LOGITS
     Duty
    1.16
    duty
    1.13
    uty
    1.01
     duty
    0.99
    naire
    0.73
    hov
    0.72
     obligation
    0.71
    ftime
    0.71
     solicitation
    0.70
    enei
    0.69
    Activations Density 0.009%

    No Known Activations