© 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. 3-RES-JB
    11. 4512
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating a change or significant impact

    oai_token-act-pair · gpt-3.5-turbo

    actions that result in someone or something being left behind or causing change

    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
    ombat
    -0.74
    uten
    -0.69
    oha
    -0.69
    oot
    -0.68
    uph
    -0.66
    urgical
    -0.66
    ixtape
    -0.66
    eg
    -0.64
    ophobia
    -0.64
    annah
    -0.64
    POSITIVE LOGITS
    LESS
    0.71
     Provided
    0.64
     aside
    0.64
    ARK
    0.64
     apart
    0.64
     conduc
    0.63
     Rooms
    0.63
    theless
    0.61
    redients
    0.60
     namely
    0.60
    Activations Density 1.124%

    No Known Activations