© 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. 7-RES-JB
    6. 7897
    Prev
    Next
    INDEX
    Explanations

    specific phrases or terms that are directly related to certain topics or concepts

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and terms related to oversight, governance, and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå
    -0.73
    arty
    -0.73
    cffff
    -0.72
    addle
    -0.71
    å§«
    -0.66
    soDeliveryDate
    -0.66
    senal
    -0.64
     sugg
    -0.64
    ãĥ´
    -0.63
    Ô
    -0.62
    POSITIVE LOGITS
    ifiers
    0.72
    ifier
    0.72
    orde
    0.64
    undown
    0.62
    orum
    0.62
    eker
    0.62
    âĦ¢
    0.62
    iuses
    0.61
     Hansen
    0.59
    asers
    0.58
    Activations Density 0.611%

    No Known Activations