© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2571
    Prev
    Next
    INDEX
    Explanations

    mentions of operating or functioning

    oai_token-act-pair · gpt-3.5-turbo

    words related to the action of functioning or conducting operations

    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
     Anger
    -0.64
     Pyrrha
    -0.62
     tears
    -0.62
     Sage
    -0.60
     Tears
    -0.59
     Pew
    -0.58
     Norn
    -0.58
    Episode
    -0.58
    aldehyde
    -0.57
     Brut
    -0.57
    POSITIVE LOGITS
     operate
    3.32
     operates
    2.45
     operated
    2.28
     operating
    1.89
     operation
    1.75
    Oper
    1.71
     Oper
    1.63
    operated
    1.62
     OPER
    1.51
     operations
    1.47
    Activations Density 0.016%

    No Known Activations