© 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. 13557
    Prev
    Next
    INDEX
    Explanations

    options or abilities that can be enabled or disabled

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to options and capabilities

    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
    irie
    -0.60
    ecause
    -0.59
    hemat
    -0.58
     Expect
    -0.57
    uilding
    -0.55
    adow
    -0.53
    agate
    -0.52
    urity
    -0.52
    driving
    -0.52
    ModLoader
    -0.51
    POSITIVE LOGITS
     to
    1.11
    to
    0.75
     of
    0.74
    pps
    0.71
     thereto
    0.70
    forts
    0.67
     To
    0.64
    umption
    0.63
    assisted
    0.63
    untarily
    0.62
    Activations Density 0.085%

    No Known Activations