© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 7822
    Prev
    Next
    INDEX
    Explanations

    combinations of different elements, such as topics, themes, or fields

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating combinations or integrations of different elements or genres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Discuss
    -0.81
     ARTICLE
    -0.78
    STAR
    -0.76
     [*
    -0.75
    Should
    -0.75
    Article
    -0.74
    _.
    -0.73
    Section
    -0.72
     Citation
    -0.72
    ":["
    -0.72
    POSITIVE LOGITS
     eclectic
    0.95
     assorted
    0.89
     quirky
    0.84
     genres
    0.81
     personalities
    0.80
     aesthetics
    0.79
     seamlessly
    0.76
     eleg
    0.76
     disparate
    0.76
     eccentric
    0.75
    Activations Density 0.357%

    No Known Activations