© 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. 10007
    Prev
    Next
    INDEX
    Explanations

    words associated with discussions or mentions of ability or possibility

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions indicating inability or impossibility

    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
     RAD
    -0.82
     airs
    -0.76
     Gleaming
    -0.67
     Sandwich
    -0.65
     mixed
    -0.65
    anwhile
    -0.65
     theaters
    -0.63
    çīĪ
    -0.62
     Trojan
    -0.61
     Hir
    -0.60
    POSITIVE LOGITS
    Ķ
    1.40
    «
    1.32
    ĵ
    1.30
    ij
    1.28
    ¼
    1.28
    ¢
    1.27
    £
    1.26
    ı
    1.23
    ķ
    1.23
    ¨
    1.22
    Activations Density 0.071%

    No Known Activations