© 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. 7966
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense that involve the ability to do something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word 'could' to identify potentiality or capability within the text

    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
    furt
    -0.69
    cedented
    -0.68
    balls
    -0.66
     Yards
    -0.61
    pires
    -0.60
    holder
    -0.60
    ente
    -0.59
    core
    -0.58
    igned
    -0.57
     honoring
    -0.57
    POSITIVE LOGITS
     feas
    1.12
     afford
    1.05
     conce
    1.01
    nt
    0.97
    adian
    0.97
     foresee
    0.93
    berra
    0.92
     muster
    0.88
     possibly
    0.87
    've
    0.87
    Activations Density 0.088%

    No Known Activations