© 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. 10025
    Prev
    Next
    INDEX
    Explanations

    terms related to common, recurring elements or traditions

    oai_token-act-pair · gpt-3.5-turbo

    references to commonly recognized or essential elements in various contexts

    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
    apor
    -0.71
    ignt
    -0.69
     coefficients
    -0.62
    oding
    -0.61
     Architects
    -0.60
     Principles
    -0.60
    ampa
    -0.59
     Engineers
    -0.59
     contracting
    -0.59
     equival
    -0.58
    POSITIVE LOGITS
    stone
    0.83
    stay
    0.83
     amongst
    0.83
     among
    0.81
     haunt
    0.78
     throughout
    0.77
    leground
    0.77
     fixture
    0.75
    phrase
    0.74
    rette
    0.73
    Activations Density 0.357%

    No Known Activations