© 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. 11-RES-JB
    11. 9195
    Prev
    Next
    INDEX
    Explanations

    instances of special characters followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.76
     tremend
    -0.69
     Zoro
    -0.68
     Tob
    -0.67
     Bak
    -0.67
     Tar
    -0.66
     Fou
    -0.66
     telev
    -0.65
     Wer
    -0.65
     streng
    -0.62
    POSITIVE LOGITS
    Ļ
    1.51
    ĵ
    1.10
    ¬
    1.08
    ħ
    1.06
    ı
    1.05
    ĸ
    1.04
    ķ
    1.01
    ª
    1.00
    ¢
    1.00
    ľ
    0.99
    Activations Density 0.356%

    No Known Activations