© 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. 4-RES-JB
    11. 8580
    Prev
    Next
    INDEX
    Explanations

    words related to linguistic terms and grammatical structures

    oai_token-act-pair · gpt-3.5-turbo

    grammatical terms and constructs related to language structure

    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
     staffing
    -0.92
     budgets
    -0.85
     Blair
    -0.78
     sustainability
    -0.77
    funding
    -0.76
     profitability
    -0.75
     rollout
    -0.75
     Budget
    -0.74
     funding
    -0.74
    eworks
    -0.73
    POSITIVE LOGITS
    tymology
    1.35
     noun
    1.16
    ËĪ
    1.14
    É
    1.09
     diction
    1.05
     pron
    1.04
     slang
    1.03
     verbs
    1.03
     vowel
    1.02
     suffix
    0.99
    Activations Density 0.609%

    No Known Activations