© 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 EvalsExportsinterp-engineNEWAPI 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. 9382
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational settings or classrooms

    oai_token-act-pair · gpt-3.5-turbo

    references to classrooms and educational environments

    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
    alez
    -0.87
    tale
    -0.81
    omy
    -0.80
    oms
    -0.80
    ulf
    -0.78
    olid
    -0.74
    don
    -0.74
    OD
    -0.73
    oway
    -0.72
    haps
    -0.72
    POSITIVE LOGITS
     walls
    0.82
     entrances
    0.79
     doors
    0.78
     floor
    0.75
     Walls
    0.73
     overflow
    0.73
     corners
    0.72
     stalls
    0.71
     divid
    0.71
    halla
    0.70
    Activations Density 0.024%

    No Known Activations