© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 7594
    Prev
    Next
    INDEX
    Explanations

    instances of someone physically knocking on something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to knocking or sounds associated with doors and windows

    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
    batch
    -0.73
    pard
    -0.69
    utan
    -0.62
    ensor
    -0.61
    cano
    -0.61
    jri
    -0.61
    cean
    -0.61
    APH
    -0.61
    auer
    -0.59
    amus
    -0.59
    POSITIVE LOGITS
     doors
    1.20
     door
    0.97
     wood
    0.93
     walls
    0.84
     gates
    0.82
     Door
    0.78
     bushes
    0.75
     Doors
    0.74
     curtains
    0.71
    door
    0.71
    Activations Density 0.084%

    No Known Activations