© 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. 7302
    Prev
    Next
    INDEX
    Explanations

    words related to exclamations and emphatic expressions

    oai_token-act-pair · gpt-3.5-turbo

    single letters or initials used as abbreviations or symbols

    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
     Presence
    -0.68
     Philips
    -0.67
     Catalyst
    -0.65
     bilingual
    -0.63
     MacArthur
    -0.63
     Conversion
    -0.63
     Keystone
    -0.62
     Hilbert
    -0.62
     influential
    -0.62
     Lever
    -0.61
    POSITIVE LOGITS
    oooo
    1.57
    aaaa
    1.53
    mmmm
    1.50
    OOOO
    1.49
    OOOOOOOO
    1.45
    oooooooo
    1.45
    ahah
    1.41
    AAAAAAAA
    1.38
    aaa
    1.35
    ooo
    1.34
    Activations Density 0.142%

    No Known Activations