© 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. 8-RES-JB
    11. 3830
    Prev
    Next
    INDEX
    Explanations

    verbs related to decision-making or actions being taken

    oai_token-act-pair · gpt-3.5-turbo

    the decision-making action of individuals

    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
    Lear
    -0.70
    clips
    -0.67
    ergy
    -0.67
    workers
    -0.66
     Explan
    -0.65
     Detected
    -0.65
    generated
    -0.64
    thumbnails
    -0.63
    accompanied
    -0.63
    valued
    -0.62
    POSITIVE LOGITS
     pursue
    1.31
     postpone
    1.23
     dedicate
    1.20
     ignore
    1.17
     donate
    1.16
     give
    1.14
     revisit
    1.12
     investigate
    1.12
     undertake
    1.09
     abandon
    1.08
    Activations Density 0.095%

    No Known Activations