© 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. 23838
    Prev
    Next
    INDEX
    Explanations

    instances of verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions of creation or transformation

    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
    sbm
    -0.51
    iasm
    -0.51
    razil
    -0.49
    ivas
    -0.48
    ilst
    -0.48
    orescent
    -0.48
    iery
    -0.48
    iances
    -0.48
    umar
    -0.47
    cohol
    -0.47
    POSITIVE LOGITS
     nonetheless
    1.16
    etheless
    0.97
     anyway
    0.97
     downright
    0.91
     nevertheless
    0.89
     awfully
    0.89
     instead
    0.88
     altogether
    0.80
     MUCH
    0.79
     quite
    0.78
    Activations Density 1.812%

    No Known Activations