© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 10736
    Prev
    Next
    INDEX
    Explanations

    words related to police operations or criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to sting operations in law enforcement 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
    ufact
    -0.81
     Supplement
    -0.69
    iasco
    -0.67
    ordan
    -0.64
    ocally
    -0.63
     Princ
    -0.62
     NCT
    -0.61
    ACTED
    -0.61
    uclear
    -0.60
    uters
    -0.59
    POSITIVE LOGITS
     sting
    1.36
    rays
    1.05
    ray
    1.03
    ega
    0.91
     Sting
    0.86
    Ray
    0.82
    tip
    0.78
    elope
    0.78
    ingly
    0.78
    iness
    0.75
    Activations Density 0.005%

    No Known Activations