© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12759
    Prev
    Next
    INDEX
    Explanations

    words related to sharpness, intensity, and contrasts

    oai_token-act-pair · gpt-3.5-turbo

    references to sharpness in various contexts

    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
     Alive
    -0.83
    FORE
    -0.75
    uthor
    -0.71
    YL
    -0.71
    pty
    -0.70
     Million
    -0.68
    ORED
    -0.68
    perty
    -0.68
    akeru
    -0.66
     Incarnation
    -0.65
    POSITIVE LOGITS
    ened
    1.48
    ening
    1.46
    est
    1.18
    ener
    1.11
    ness
    1.03
    eners
    1.00
     edges
    0.99
    eness
    0.90
     contrasts
    0.86
    itudinal
    0.86
    Activations Density 0.035%

    No Known Activations