© 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. 10-RES-JB
    11. 16554
    Prev
    Next
    INDEX
    Explanations

    technical terms or specifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technical specifications and engineering details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stellar
    -0.83
    naire
    -0.77
    velt
    -0.75
    lain
    -0.71
    rage
    -0.71
     Sheen
    -0.69
    imately
    -0.69
     Chamberlain
    -0.69
    ollar
    -0.69
    SHIP
    -0.65
    POSITIVE LOGITS
    ities
    1.05
     specifications
    1.05
     feasibility
    1.00
     advancements
    0.98
     advances
    0.96
    ity
    0.96
     difficulties
    0.95
    iencies
    0.93
     prowess
    0.93
     specs
    0.91
    Activations Density 0.034%

    No Known Activations