© 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. 0-RES-JB
    11. 13468
    Prev
    Next
    INDEX
    Explanations

    words related to financial resources or funding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enhancing or improving various aspects of life

    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
     Maker
    -0.66
     jails
    -0.61
     man
    -0.61
     Jah
    -0.60
     suff
    -0.60
     Jar
    -0.60
     sealed
    -0.59
     WS
    -0.58
     known
    -0.57
     wheelchair
    -0.56
    POSITIVE LOGITS
    ancing
    4.25
    anced
    3.59
    ances
    2.71
    ancers
    2.45
    ancer
    2.24
    ance
    2.19
    ANCE
    2.02
    ANC
    1.94
    anc
    1.41
    antically
    1.27
    Activations Density 0.015%

    No Known Activations