© 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. 9-RES-JB
    11. 18314
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a strong focus or emphasis on a particular concept or aspect

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing singular importance or exclusivity

    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
    ahime
    -0.81
     [|
    -0.80
    tnc
    -0.79
    enture
    -0.68
    utenberg
    -0.65
    assetsadobe
    -0.65
    asty
    -0.64
     unfocusedRange
    -0.63
    ruct
    -0.63
    umbn
    -0.62
    POSITIVE LOGITS
     imaginable
    1.02
     conceivable
    1.00
     remaining
    0.98
     remotely
    0.93
     sane
    0.91
     whatsoever
    0.85
     EVER
    0.83
    soever
    0.82
     surviving
    0.82
     ever
    0.82
    Activations Density 0.140%

    No Known Activations