© 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. 10-RES-JB
    11. 14029
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Crit" or variations of it such as critique or criticized

    oai_token-act-pair · gpt-3.5-turbo

    references to critiques or criticism, particularly related to media or public figures

    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
    velt
    -0.74
    orthy
    -0.73
    UTH
    -0.65
     Petty
    -0.65
     Aad
    -0.63
     Shades
    -0.62
     Stephenson
    -0.61
     Faust
    -0.60
    noon
    -0.60
     Cere
    -0.57
    POSITIVE LOGITS
    erion
    1.60
    icism
    1.50
    ique
    1.41
    iques
    1.36
    eria
    1.35
    iqu
    1.19
    ically
    1.16
    ters
    1.16
    ic
    1.03
    ter
    1.02
    Activations Density 0.035%

    No Known Activations