© 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. 2-RES-JB
    11. 1489
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cables."

    oai_token-act-pair · gpt-3.5-turbo

    references to cables and related wiring components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zai
    -0.75
    estate
    -0.70
    Islamic
    -0.68
    iesta
    -0.68
    iak
    -0.68
    Syrian
    -0.66
    administ
    -0.66
     Democr
    -0.65
    lied
    -0.64
    Star
    -0.64
    POSITIVE LOGITS
     cables
    1.62
     cable
    1.09
     cords
    0.99
     wires
    0.99
     connectors
    0.92
     ropes
    0.90
    mith
    0.88
     seams
    0.87
     cord
    0.87
     wiring
    0.86
    Activations Density 0.022%

    No Known Activations