© 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. 6-RES-JB
    11. 19752
    Prev
    Next
    INDEX
    Explanations

    locations described as "garage"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "garage."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uality
    -0.95
    emic
    -0.88
    lihood
    -0.85
    ivia
    -0.81
    vironment
    -0.81
    ciating
    -0.80
     Archdemon
    -0.79
    uador
    -0.75
    ebus
    -0.73
    ologue
    -0.73
    POSITIVE LOGITS
     garage
    1.09
     doors
    1.01
     door
    0.99
     attic
    0.94
     Door
    0.92
    door
    0.91
     Garage
    0.80
    rats
    0.79
     turrets
    0.78
     lid
    0.78
    Activations Density 0.019%

    No Known Activations