© 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. 14878
    Prev
    Next
    INDEX
    Explanations

    phrases related to exerting force or influence towards a specific direction

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pull" in various contexts

    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
    bats
    -0.79
     Certain
    -0.75
    DEN
    -0.70
    etus
    -0.69
    equality
    -0.68
    esan
    -0.68
    teen
    -0.67
    asonable
    -0.66
     Hosp
    -0.66
    thel
    -0.66
    POSITIVE LOGITS
     pull
    3.44
    Pull
    2.46
     Pull
    2.36
    pull
    2.28
     pulls
    2.18
     pulling
    1.97
     pulled
    1.82
     push
    1.54
     squeeze
    1.54
     lift
    1.32
    Activations Density 0.018%

    No Known Activations