© 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. 4102
    Prev
    Next
    INDEX
    Explanations

    words related to fixing or improving a situation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to remedial assistance and queries about data or processes

    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
    anwhile
    -0.83
     Luxembourg
    -0.66
    finder
    -0.65
     Ago
    -0.65
     Centauri
    -0.65
     KING
    -0.65
    crop
    -0.63
    othal
    -0.62
     Sans
    -0.60
     Metropolitan
    -0.60
    POSITIVE LOGITS
    iated
    1.09
    ises
    1.07
    iation
    1.07
    iating
    1.04
    ising
    1.02
    iates
    1.02
    icating
    0.97
    ial
    0.97
    ying
    0.97
    ved
    0.96
    Activations Density 0.018%

    No Known Activations