© 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. 3-RES-JB
    6. 9550
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the option or ability to change or switch something

    oai_token-act-pair · gpt-3.5-turbo

    commands related to toggling visibility and image options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ded
    -0.70
    esses
    -0.68
    metic
    -0.68
    bats
    -0.67
    sup
    -0.66
    orkshire
    -0.65
    dating
    -0.65
    wagen
    -0.64
    ivas
    -0.59
    naires
    -0.59
    POSITIVE LOGITS
     toggle
    1.11
    toggle
    0.80
     caption
    0.75
    Enlarge
    0.75
     captcha
    0.70
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.70
    aukee
    0.70
    pmwiki
    0.69
    APE
    0.68
     "$:/
    0.64
    Activations Density 0.005%

    No Known Activations