© 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. 6-RES-JB
    11. 9221
    Prev
    Next
    INDEX
    Explanations

    sentences related to legal sentences or judgments

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the duration of time related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOW
    -0.68
    pointers
    -0.63
    WHERE
    -0.63
    rily
    -0.60
    onica
    -0.60
    #$
    -0.60
     %%
    -0.57
    campus
    -0.56
    ONSORED
    -0.56
    deck
    -0.56
    POSITIVE LOGITS
    clusively
    0.96
     accordance
    0.95
    activity
    0.93
    patient
    0.92
    clusive
    0.92
    clus
    0.89
    ordinate
    0.88
     favor
    0.87
     relation
    0.87
    authent
    0.86
    Activations Density 0.224%

    No Known Activations