© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 3144
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons and measurements

    oai_token-act-pair · gpt-3.5-turbo

    quantitative comparisons and measurements related to health or environmental impact

    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
     scapego
    -0.68
     announcements
    -0.67
     privatization
    -0.67
     acknowled
    -0.67
     reneg
    -0.66
     banners
    -0.65
     blame
    -0.65
     themes
    -0.63
     decorations
    -0.63
     antagonists
    -0.63
    POSITIVE LOGITS
    average
    1.05
     multiplied
    1.03
    assuming
    1.00
     average
    0.98
     equivalent
    0.96
     Assuming
    0.92
    Assuming
    0.92
     equals
    0.90
     averages
    0.90
    $$
    0.89
    Activations Density 1.126%

    No Known Activations