© 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. 0-RES-JB
    11. 1588
    Prev
    Next
    INDEX
    Explanations

    verbs related to pushing or promoting actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "pushed" related to social or political pressures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confession
    -0.70
    odor
    -0.66
     Nos
    -0.65
    seys
    -0.64
    onyms
    -0.64
     oath
    -0.64
    worthiness
    -0.62
     Stain
    -0.61
     Uniform
    -0.61
     appraisal
    -0.60
    POSITIVE LOGITS
     pushed
    3.19
     shoved
    2.05
     pushes
    1.84
     pressed
    1.78
     bumped
    1.75
     push
    1.74
     pushing
    1.69
     pulled
    1.63
     pressured
    1.62
     squeezed
    1.60
    Activations Density 0.011%

    No Known Activations