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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 6974
    Prev
    Next
    INDEX
    Explanations

    mentions of physical spaces, particularly corridors

    oai_token-act-pair · gpt-3.5-turbo

    references to infrastructure pathways or routes

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

    No Comments

    Negative Logits
    itude
    -0.84
    iak
    -0.80
    odium
    -0.70
    estamp
    -0.70
    sonian
    -0.69
    itsu
    -0.69
    oras
    -0.69
    icio
    -0.68
    olute
    -0.67
    hur
    -0.67
    POSITIVE LOGITS
     corridors
    1.08
     corridor
    1.00
    ridor
    0.97
     Corridor
    0.93
     routes
    0.85
     passages
    0.81
    ways
    0.80
    ttes
    0.79
    way
    0.78
     route
    0.77
    Activations Density 0.016%

    No Known Activations