© 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. 6-RES-JB
    11. 23723
    Prev
    Next
    INDEX
    Explanations

    instances of words related to physical scarring

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "scar" and its variations, indicating a focus on the concept of scarring or the effects of scars in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.81
    gaard
    -0.75
    ablishment
    -0.74
    £ı
    -0.73
    hower
    -0.71
    ullivan
    -0.70
    ostics
    -0.68
    gencies
    -0.68
    guyen
    -0.67
    ablish
    -0.66
    POSITIVE LOGITS
    ring
    1.05
    red
    1.02
    lets
    0.93
    crow
    0.92
    fed
    0.90
    fing
    0.88
    face
    0.87
    abs
    0.85
    pered
    0.85
    uler
    0.84
    Activations Density 0.033%

    No Known Activations