© 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. 13678
    Prev
    Next
    INDEX
    Explanations

    phrases related to suspicion and certainty

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that indicate certainty or obviousness in statements

    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
    ordable
    -0.81
    catentry
    -0.74
    venant
    -0.74
    "},
    -0.66
    orest
    -0.63
    ogue
    -0.62
    vert
    -0.61
    ruciating
    -0.61
    azeera
    -0.60
    Appearances
    -0.60
    POSITIVE LOGITS
     intended
    1.17
     intend
    1.15
     subconscious
    1.09
     sensed
    1.07
     misunderstood
    1.07
     intending
    1.05
     sincerely
    1.04
     genuinely
    1.03
     underestimated
    1.02
     sincere
    1.02
    Activations Density 0.360%

    No Known Activations