© 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. 11406
    Prev
    Next
    INDEX
    Explanations

    phrases that express varying degrees of certainty or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a consequence or condition

    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
    ucc
    -0.74
     guiActiveUnfocused
    -0.67
    "},"
    -0.64
    leneck
    -0.64
    gat
    -0.63
    ufact
    -0.60
    robe
    -0.59
    fare
    -0.59
    atti
    -0.57
    ews
    -0.56
    POSITIVE LOGITS
     coupled
    1.21
     incidentally
    1.08
     combined
    1.00
     plus
    0.97
     however
    0.93
     alas
    0.89
     along
    0.87
     needless
    0.84
     sadly
    0.83
     admittedly
    0.82
    Activations Density 0.078%

    No Known Activations