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. 8-RES-JB
    6. 15882
    Prev
    Next
    INDEX
    Explanations

    information related to police investigations, arrests, and crime

    oai_token-act-pair · gpt-3.5-turbo

    information related to crime incidents and police activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     filib
    -0.73
    lip
    -0.70
    bench
    -0.69
     mog
    -0.68
     contrace
    -0.68
     lect
    -0.67
    tes
    -0.67
    gemony
    -0.66
    hett
    -0.66
    mill
    -0.65
    POSITIVE LOGITS
    intendent
    0.94
     detectives
    0.93
     coroner
    0.92
    nsics
    0.89
     Investigators
    0.89
    Investigators
    0.88
    EMS
    0.87
     paramedics
    0.84
    arnaev
    0.82
    Authorities
    0.81
    Activations Density 0.562%

    No Known Activations