© 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 EvalsExportsinterp-engineNEWAPI 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. 24398
    Prev
    Next
    INDEX
    Explanations

    ASCII art representations of geometric shapes

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols used in formatting or layout

    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
     proble
    -0.79
    conservancy
    -0.76
     endors
    -0.74
     consequential
    -0.72
     viability
    -0.71
     skelet
    -0.69
     sponsor
    -0.69
     tremend
    -0.69
     retrospective
    -0.69
    hement
    -0.68
    POSITIVE LOGITS
    -.
    1.28
    -|
    1.21
    =(
    1.19
    -'
    1.17
    =/
    1.16
    -+
    1.14
    ~
    1.12
    =
    1.11
    ++++
    1.11
    <
    1.10
    Activations Density 0.158%

    No Known Activations