© 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. 4-RES-JB
    11. 7450
    Prev
    Next
    INDEX
    Explanations

    terms indicating a specific level of certainty or precision

    oai_token-act-pair · gpt-3.5-turbo

    the word "exactly" and its various contextual usages

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

    No Comments

    Negative Logits
    rift
    -0.82
    ULTS
    -0.69
    olyn
    -0.69
    ysc
    -0.69
     Guys
    -0.68
    ERAL
    -0.67
    tein
    -0.65
    hung
    -0.65
     Vaj
    -0.64
    ems
    -0.64
    POSITIVE LOGITS
    anus
    0.68
     novel
    0.62
    acement
    0.61
     pronounce
    0.60
     chronological
    0.60
    ifiable
    0.60
    lishes
    0.60
     synonymous
    0.59
     divorced
    0.59
     anymore
    0.59
    Activations Density 0.007%

    No Known Activations