© 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
    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. 17748
    Prev
    Next
    INDEX
    Explanations

    words related to retractions or corrections in written content

    oai_token-act-pair · gpt-3.5-turbo

    references to corrections or reactions in reports or statements

    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
    SHIP
    -0.78
    tips
    -0.73
    STEM
    -0.70
    ï¸
    -0.67
    STD
    -0.66
    WAYS
    -0.66
    )=(
    -0.65
    Shell
    -0.64
    latest
    -0.64
    ãĥĨãĤ£
    -0.63
    POSITIVE LOGITS
    ainer
    1.19
    ribut
    1.18
    raction
    1.14
    reating
    1.08
    rans
    1.06
    ention
    1.04
    itled
    1.01
    rieve
    1.01
    raining
    1.00
    reat
    0.99
    Activations Density 0.014%

    No Known Activations