© 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. 20325
    Prev
    Next
    INDEX
    Explanations

    sequences starting and ending with special characters used for indicating sections or formatting in text

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or symbol frequently and its variations or representations

    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
     Sau
    -0.77
     Franch
    -0.74
     Lerner
    -0.72
     princ
    -0.70
     antip
    -0.69
     Nikola
    -0.69
     Mul
    -0.69
     snail
    -0.68
     Henri
    -0.68
     Nelson
    -0.68
    POSITIVE LOGITS
    Ŀ
    2.04
    ¡
    1.47
    Ł
    1.42
    ¤
    1.36
    ©
    1.36
    ª
    1.36
    °
    1.35
    ŀ
    1.32
    ľ
    1.32
    ī
    1.30
    Activations Density 0.209%

    No Known Activations