© 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
    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. 14882
    Prev
    Next
    INDEX
    Explanations

    phrases indicating composition or makeup

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating composition or makeup of entities

    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
    ahime
    -0.72
     clarity
    -0.67
     clarification
    -0.62
    idge
    -0.60
    ç«
    -0.59
     direction
    -0.59
    visor
    -0.58
    found
    -0.57
    ipeg
    -0.56
     blinded
    -0.56
    POSITIVE LOGITS
     chiefly
    1.06
     principally
    0.94
     mainly
    0.89
     primarily
    0.86
     solely
    0.84
     entirely
    0.83
    ertodd
    0.83
     loosely
    0.82
     mostly
    0.79
    icle
    0.76
    Activations Density 0.051%

    No Known Activations