© 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. 10-RES-JB
    11. 676
    Prev
    Next
    INDEX
    Explanations

    words related to strong or significant impact or change

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dramatic" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pring
    -0.77
    heit
    -0.73
    iband
    -0.72
    PLIED
    -0.72
    roma
    -0.70
    rity
    -0.70
    amina
    -0.69
    pires
    -0.69
    adr
    -0.68
    owship
    -0.68
    POSITIVE LOGITS
     turnaround
    1.04
     departure
    1.04
     transformations
    1.03
     departures
    1.02
     change
    1.01
     changes
    0.98
     shifts
    0.97
     reversal
    0.95
     reductions
    0.92
     differences
    0.91
    Activations Density 0.065%

    No Known Activations