© 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. 12541
    Prev
    Next
    INDEX
    Explanations

    actions or events related to competition, performance, achievement, or physical abilities

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented verbs that convey achievement or failure

    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
    76561
    -0.66
     externalToEVAOnly
    -0.66
     encount
    -0.66
    é¾įå
    -0.64
     forgetting
    -0.62
     istg
    -0.62
     msec
    -0.62
     aug
    -0.62
    [_
    -0.59
     oblig
    -0.59
    POSITIVE LOGITS
    escape
    0.92
    able
    0.92
    ingly
    0.91
    ables
    0.85
    eworks
    0.85
     theirs
    0.83
    ibles
    0.82
    leaf
    0.81
    pipe
    0.80
    estyle
    0.79
    Activations Density 0.207%

    No Known Activations