© 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. 5135
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by actions or interactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or processes

    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
     Conditions
    -0.59
     ILCS
    -0.58
    enegger
    -0.56
    MI
    -0.55
    iac
    -0.55
    heed
    -0.54
    wcsstore
    -0.54
     currently
    -0.54
     now
    -0.53
     presently
    -0.53
    POSITIVE LOGITS
     enthusi
    0.68
     last
    0.67
    âĹ¼
    0.64
     unheard
    0.60
    使
    0.60
     LAST
    0.59
     earlier
    0.58
     yesterday
    0.58
     atro
    0.56
    perty
    0.56
    Activations Density 1.002%

    No Known Activations