© 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. 0-RES-JB
    6. 1433
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "says"

    oai_token-act-pair · gpt-3.5-turbo

    statements attributed to speakers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suitable
    -0.57
     prox
    -0.56
    animate
    -0.55
    EStreamFrame
    -0.55
     alternate
    -0.54
    rive
    -0.54
     present
    -0.54
     merit
    -0.53
    rued
    -0.52
    onet
    -0.52
    POSITIVE LOGITS
     says
    3.08
     Says
    2.50
     insists
    1.99
     SAY
    1.98
     tells
    1.93
     explains
    1.92
     warns
    1.89
     argues
    1.88
     alleges
    1.85
     admits
    1.83
    Activations Density 0.060%

    No Known Activations