© 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. 19237
    Prev
    Next
    INDEX
    Explanations

    terms related to evidence or verification

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "proof" in various contexts

    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
     livest
    -0.75
    artney
    -0.73
    ideshow
    -0.71
     Osc
    -0.71
    cffffcc
    -0.69
     Peninsula
    -0.69
     contrace
    -0.67
    ufact
    -0.64
    ktop
    -0.63
     Parenthood
    -0.62
    POSITIVE LOGITS
    reading
    1.24
    reader
    1.12
    read
    1.03
    edly
    0.96
    reads
    0.83
     proofs
    0.82
    proof
    0.80
     proof
    0.80
    ificate
    0.80
    uers
    0.78
    Activations Density 0.024%

    No Known Activations