© 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. 9-RES-JB
    11. 23354
    Prev
    Next
    INDEX
    Explanations

    phrases related to power, control, and authority

    oai_token-act-pair · gpt-3.5-turbo

    key functional words or phrases related to actions and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charism
    -0.65
     Helm
    -0.64
     اÙĦ
    -0.64
    ¥ŀ
    -0.61
     Seym
    -0.61
     Reilly
    -0.61
     millenn
    -0.59
    à©
    -0.59
    ð
    -0.59
     Paste
    -0.58
    POSITIVE LOGITS
    wed
    0.92
    ividual
    0.89
    wolves
    0.88
    lled
    0.83
    stood
    0.80
    alian
    0.77
     wont
    0.77
    erent
    0.76
     selves
    0.76
    ancial
    0.75
    Activations Density 0.995%

    No Known Activations