© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 10033
    Prev
    Next
    INDEX
    Explanations

    references to materials and components like aluminum, copper, steel, and glass in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    materials mentioned in relation to construction and manufacturing

    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
    arenthood
    -0.82
    onym
    -0.77
    OPA
    -0.75
    international
    -0.74
     Indigo
    -0.73
    dL
    -0.73
    recent
    -0.72
    yssey
    -0.71
    achu
    -0.71
    atch
    -0.70
    POSITIVE LOGITS
     coffin
    1.13
     casing
    1.11
     cylinder
    1.09
     alloy
    1.03
     slab
    1.01
     panels
    1.01
     clad
    1.00
     rods
    0.97
     enclosure
    0.97
     oxide
    0.96
    Activations Density 0.175%

    No Known Activations