© 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. 20393
    Prev
    Next
    INDEX
    Explanations

    specific mentions or emphasis of the word "exact"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "exact" and its variations

    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
    ©¶æ
    -0.76
    aido
    -0.74
     Beware
    -0.71
     Dise
    -0.70
     Fever
    -0.69
     ashore
    -0.64
    ulton
    -0.63
    itton
    -0.63
     Nare
    -0.62
     Azerb
    -0.61
    POSITIVE LOGITS
    ity
    1.41
    ities
    1.12
     wording
    1.07
     numbers
    0.88
     embodiments
    0.87
    izations
    0.87
     implementation
    0.87
    aneous
    0.86
    iating
    0.86
    izable
    0.85
    Activations Density 0.067%

    No Known Activations