© 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. 8-RES-JB
    11. 3276
    Prev
    Next
    INDEX
    Explanations

    references to physical locations within a setting, particularly describing different areas within a space like walls, floors, ceilings, and outside locations

    oai_token-act-pair · gpt-3.5-turbo

    references to physical locations or surfaces within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rosso
    -0.88
    anson
    -0.74
    anol
    -0.72
     Moves
    -0.69
    Ô
    -0.67
    olkien
    -0.66
    ãĥĩ
    -0.65
    edIn
    -0.65
    alin
    -0.65
    ortium
    -0.64
    POSITIVE LOGITS
     ceiling
    1.04
    boards
    1.00
     porch
    0.92
     balcony
    0.88
     railing
    0.88
     floor
    0.88
     grate
    0.87
     wip
    0.87
     pedest
    0.87
     doorway
    0.87
    Activations Density 0.214%

    No Known Activations