© 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. 21808
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptive words related to intensity and seriousness

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "mean" and words associated with significance or interpretation

    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
    authorized
    -0.76
    Downloadha
    -0.64
     Seym
    -0.64
    =~
    -0.62
    avia
    -0.62
    akeru
    -0.61
     conduc
    -0.60
    lished
    -0.60
     Takeru
    -0.59
    rien
    -0.58
    POSITIVE LOGITS
    ly
    1.39
    est
    1.34
    ness
    1.23
    nesses
    1.14
    LY
    1.04
    itude
    1.03
    sounding
    0.91
    hearted
    0.90
    ening
    0.89
    founded
    0.86
    Activations Density 0.171%

    No Known Activations