© 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. 9-RES-JB
    11. 2421
    Prev
    Next
    INDEX
    Explanations

    definite articles 'the'

    oai_token-act-pair · gpt-3.5-turbo

    recurring phrases emphasizing "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įåĸļ士
    -0.80
    oros
    -0.79
    apons
    -0.71
    these
    -0.71
    anches
    -0.68
    js
    -0.68
    berries
    -0.67
    ãĥīãĥ©
    -0.67
    iques
    -0.67
    isson
    -0.67
    POSITIVE LOGITS
     extent
    1.06
     same
    1.06
     gist
    1.00
     culmination
    0.98
     closest
    0.97
     easiest
    0.95
     longest
    0.95
     conclusion
    0.94
     type
    0.93
     toughest
    0.92
    Activations Density 0.128%

    No Known Activations