© 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. 1-RES-JB
    6. 16014
    Prev
    Next
    INDEX
    Explanations

    terms related to collision or coming together

    oai_token-act-pair · gpt-3.5-turbo

    references to data collection or aggregation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qua
    -0.73
    DragonMagazine
    -0.68
    ItemTracker
    -0.67
    Myth
    -0.66
    scribe
    -0.66
    ARK
    -0.65
     Declaration
    -0.65
    nos
    -0.65
    ¥µ
    -0.64
    emonic
    -0.64
    POSITIVE LOGITS
     coll
    1.01
    ibrary
    0.82
    alez
    0.82
    iseum
    0.80
    ocation
    0.77
    coll
    0.75
    halla
    0.75
    oqu
    0.74
    imation
    0.73
    imer
    0.72
    Activations Density 0.004%

    No Known Activations