© 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. 8-RES-JB
    11. 20513
    Prev
    Next
    INDEX
    Explanations

    contractions of "do not" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    negations or contractions used to express denial or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antioxid
    -0.78
    interstitial
    -0.76
    =-=-=-=-=-=-=-=-
    -0.71
    wrapper
    -0.70
    assemb
    -0.65
    Maker
    -0.64
     Maiden
    -0.63
     Continued
    -0.63
    £ı
    -0.62
     Onion
    -0.61
    POSITIVE LOGITS
     hesitate
    1.20
     necessarily
    1.10
     realise
    1.06
     bother
    1.06
     realize
    1.03
     specify
    0.99
     disappoint
    0.93
     initially
    0.92
     anticipate
    0.91
     survive
    0.91
    Activations Density 0.124%

    No Known Activations