© 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. 19189
    Prev
    Next
    INDEX
    Explanations

    instances of physical movement or relocation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "moved."

    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
    amin
    -0.62
     Prophe
    -0.61
    bies
    -0.60
     everyday
    -0.60
     basal
    -0.58
     risk
    -0.57
     authentication
    -0.57
     serum
    -0.56
     prescription
    -0.56
    oir
    -0.56
    POSITIVE LOGITS
     moved
    3.35
     relocated
    2.25
     shifted
    2.00
     migrated
    1.90
     transitioned
    1.71
     move
    1.63
     moves
    1.56
     drifted
    1.50
     progressed
    1.49
     rotated
    1.49
    Activations Density 0.020%

    No Known Activations