© 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. 1-RES-JB
    11. 14579
    Prev
    Next
    INDEX
    Explanations

    phrases or words indicating extreme negativity or criticism

    oai_token-act-pair · gpt-3.5-turbo

    the word "utter" and its variations to indicate strong emphasis or negative evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pei
    -0.79
    amsung
    -0.79
    apego
    -0.71
    oult
    -0.70
    anwhile
    -0.69
    xual
    -0.67
    aspberry
    -0.67
    OHN
    -0.67
    elled
    -0.67
    abbit
    -0.66
    POSITIVE LOGITS
     utter
    1.14
    ance
    0.84
    ances
    0.83
     uttered
    0.81
     aloud
    0.80
     amaz
    0.80
    TY
    0.76
    ingly
    0.76
    çIJ
    0.73
    nesses
    0.71
    Activations Density 0.003%

    No Known Activations