© 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. 16544
    Prev
    Next
    INDEX
    Explanations

    terms related to unexpected or unwanted occurrences

    oai_token-act-pair · gpt-3.5-turbo

    variations of the prefix "uns-" indicating negation or absence

    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
    ãĥ¼ãĥĨãĤ£
    -0.67
    SHIP
    -0.66
     Rams
    -0.66
    eur
    -0.64
     Sons
    -0.63
     lions
    -0.63
    Reviewer
    -0.63
     Hastings
    -0.62
     Dynamics
    -0.62
     Guardians
    -0.60
    POSITIVE LOGITS
    olicited
    1.51
    aturated
    1.35
    aved
    1.32
    atisf
    1.31
    ustain
    1.29
    avour
    1.27
    ourced
    1.27
    ocial
    1.24
    killed
    1.23
    chool
    1.23
    Activations Density 0.011%

    No Known Activations