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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 8912
    Prev
    Next
    INDEX
    Explanations

    phrases related to people being present at specific locations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities involved in investigations or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orically
    -0.75
    ags
    -0.66
    awatts
    -0.66
    agos
    -0.61
    ians
    -0.60
    auga
    -0.59
    acters
    -0.58
    DragonMagazine
    -0.58
    printf
    -0.58
    ns
    -0.57
    POSITIVE LOGITS
     standby
    1.11
     duty
    1.05
     board
    1.05
    site
    0.99
     probation
    0.99
     vacation
    0.95
     assignment
    0.94
     hiatus
    0.92
     leash
    0.88
     lookout
    0.87
    Activations Density 0.121%

    No Known Activations