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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 632
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical movement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "moving."

    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
    geon
    -0.71
    ame
    -0.70
    û
    -0.69
    kat
    -0.69
    fits
    -0.66
    awar
    -0.66
    bey
    -0.65
    arth
    -0.65
    emia
    -0.64
    esame
    -0.61
    POSITIVE LOGITS
     moving
    3.32
    moving
    2.31
     Moving
    2.27
    Moving
    2.07
     shifting
    1.70
     migrating
    1.66
     move
    1.51
     moved
    1.51
     transitioning
    1.50
     rotating
    1.49
    Activations Density 0.020%

    No Known Activations