© 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. 4-RES-JB
    6. 6551
    Prev
    Next
    INDEX
    Explanations

    references to evidence or proof in political contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to evidence or proof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Evidence

    No Comments

    Negative Logits
    ategory
    -0.85
    otom
    -0.77
     throats
    -0.72
    ÃŁ
    -0.68
    isner
    -0.66
    patch
    -0.66
    ovie
    -0.66
    oos
    -0.65
    uckle
    -0.64
    awar
    -0.64
    POSITIVE LOGITS
    evidence
    1.01
     evidence
    0.99
     proof
    0.93
    edly
    0.91
    proof
    0.90
     Evidence
    0.86
    Evidence
    0.85
     corrobor
    0.84
     conclusive
    0.79
     proofs
    0.78
    Activations Density 0.024%

    No Known Activations