© 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. 11-RES-JB
    11. 10025
    Prev
    Next
    INDEX
    Explanations

    terms related to government and military

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government and military contexts

    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
    ogie
    -0.72
    onement
    -0.68
    upper
    -0.65
    equal
    -0.65
    nesty
    -0.64
    again
    -0.64
    arations
    -0.64
     Sharon
    -0.63
    ledge
    -0.62
    ukong
    -0.61
    POSITIVE LOGITS
     scanners
    1.06
     applications
    1.02
     databases
    0.99
     sensors
    0.97
     printers
    0.95
     IoT
    0.95
     electronics
    0.95
     satellites
    0.91
     sensor
    0.91
     datasets
    0.90
    Activations Density 0.449%

    No Known Activations