© 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. 6-RES-JB
    11. 5637
    Prev
    Next
    INDEX
    Explanations

    modal verbs expressing possibility, necessity, or permission

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs and expressions of capability or possibility

    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
     Echoes
    -0.67
    hler
    -0.66
     Plane
    -0.64
    DIV
    -0.64
    onductor
    -0.63
     Nanto
    -0.62
     Wage
    -0.61
     Drain
    -0.61
     Orchestra
    -0.61
     Mash
    -0.59
    POSITIVE LOGITS
    able
    0.92
    runs
    0.83
    tan
    0.81
    anc
    0.79
    iful
    0.78
    full
    0.77
    ier
    0.77
    rams
    0.77
    fully
    0.75
    oub
    0.75
    Activations Density 0.611%

    No Known Activations