© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 19785
    Prev
    Next
    INDEX
    Explanations

    direct speech indicating communication of an event or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "told."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.77
    icons
    -0.73
    adesh
    -0.70
    engeance
    -0.68
    abilities
    -0.67
    ilings
    -0.64
    pite
    -0.64
    posure
    -0.64
    reci
    -0.64
    otion
    -0.64
    POSITIVE LOGITS
    tale
    1.14
    tell
    0.95
     Tell
    0.81
    warn
    0.76
    told
    0.76
     tells
    0.75
     bluntly
    0.74
    ingly
    0.74
     told
    0.74
     BuzzFeed
    0.73
    Activations Density 0.059%

    No Known Activations