© 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. 22284
    Prev
    Next
    INDEX
    Explanations

    adjectives related to intensity or impact

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas, suggesting a focus on sentence structure and complexity

    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
    ãĥ¯
    -0.72
    ":[
    -0.71
    prise
    -0.69
    ãĥīãĥ©
    -0.69
    orem
    -0.68
    ãģł
    -0.65
    ystem
    -0.65
    Else
    -0.64
    imize
    -0.64
    =#
    -0.63
    POSITIVE LOGITS
     although
    1.15
     however
    1.14
     though
    1.11
     owing
    1.09
     but
    1.08
     preferring
    1.03
     except
    0.97
     albeit
    0.96
     consisting
    0.95
     averaging
    0.92
    Activations Density 0.364%

    No Known Activations