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. 9-RES-JB
    6. 21596
    Prev
    Next
    INDEX
    Explanations

    reports of different types of incidents or emergencies being responded to by authorities

    oai_token-act-pair · gpt-3.5-turbo

    incidents related to reports of criminal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.85
    ãĤ´ãĥ³
    -0.80
    TED
    -0.74
    izons
    -0.73
     evaluates
    -0.73
    Bonus
    -0.71
    wikipedia
    -0.71
    isSpecialOrderable
    -0.70
    âĨij
    -0.69
    displayText
    -0.69
    POSITIVE LOGITS
     disturbance
    1.25
     disturbances
    1.22
     gunshots
    1.14
     gunfire
    1.03
     intruder
    0.97
     unidentified
    0.95
     unexplained
    0.94
     burgl
    0.93
     burglary
    0.91
     sightings
    0.90
    Activations Density 0.333%

    No Known Activations