© 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. 10414
    Prev
    Next
    INDEX
    Explanations

    words or phrases suggesting doubt or concern

    oai_token-act-pair · gpt-3.5-turbo

    terms related to questionable or dubious practices and situations

    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
    eding
    -0.86
    ften
    -0.85
    olon
    -0.84
    OVA
    -0.82
    eded
    -0.78
    hower
    -0.77
    elf
    -0.75
    ynthesis
    -0.74
    hner
    -0.73
    iser
    -0.73
    POSITIVE LOGITS
     questionable
    1.09
     dubious
    1.04
     legality
    0.91
     suspic
    0.77
     foul
    0.70
     spurious
    0.68
     commodities
    0.68
     Mub
    0.67
     Thomson
    0.66
     antiquity
    0.66
    Activations Density 0.009%

    No Known Activations