© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 7120
    Prev
    Next
    INDEX
    Explanations

    verbs related to decision-making and actions

    oai_token-act-pair · gpt-3.5-turbo

    action verbs and their variations related to discussions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secondary
    -0.70
     interference
    -0.68
     complying
    -0.67
     unfavorable
    -0.66
     effective
    -0.65
     cooler
    -0.65
     downstream
    -0.65
     transact
    -0.64
     objective
    -0.64
     stagnant
    -0.63
    POSITIVE LOGITS
    wrote
    1.27
    ifies
    1.11
    ulates
    1.03
    izes
    1.01
    ounces
    1.00
    aciously
    0.98
    okingly
    0.98
    itates
    0.97
    isively
    0.96
    ounced
    0.95
    Activations Density 0.244%

    No Known Activations