© 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. 12653
    Prev
    Next
    INDEX
    Explanations

    the symbol 'âĢ' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "do" in various negated forms

    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
     Mous
    -0.73
     Manit
    -0.72
     mainland
    -0.70
    ilee
    -0.68
     Franch
    -0.66
     snail
    -0.66
    anwhile
    -0.63
    illary
    -0.63
     Nept
    -0.62
     shepherd
    -0.62
    POSITIVE LOGITS
    Ŀ
    1.40
    ľ
    1.39
    ¡
    1.32
    °
    1.14
    ¿
    1.13
    ¼
    1.13
    Ķ
    1.11
    Ń
    1.09
    ¦
    1.07
    Ł
    1.04
    Activations Density 0.287%

    No Known Activations