© 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. 7-RES-JB
    11. 24044
    Prev
    Next
    INDEX
    Explanations

    verbs denoting actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    active verbs related to decision-making or legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ersen
    -0.75
    ussen
    -0.72
    nown
    -0.70
    ère
    -0.68
    behind
    -0.68
    itars
    -0.67
    retty
    -0.65
    olini
    -0.65
    ici
    -0.64
    dream
    -0.63
    POSITIVE LOGITS
     materials
    0.72
     regard
    0.71
     engagements
    0.71
     directions
    0.69
     foreign
    0.64
    enance
    0.63
     decisions
    0.63
     habitable
    0.63
     purposes
    0.62
     admissions
    0.62
    Activations Density 0.211%

    No Known Activations