© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 20898
    Prev
    Next
    INDEX
    Explanations

    phrases related to lists of specific examples

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to various additional topics or elements associated with a primary subject

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

    No Comments

    Negative Logits
    INAL
    -0.76
     2024
    -0.75
    ukong
    -0.72
     2021
    -0.68
     Nid
    -0.68
     1965
    -0.67
    rian
    -0.67
     2025
    -0.67
    ister
    -0.66
     2020
    -0.65
    POSITIVE LOGITS
    umbn
    0.86
    milo
    0.80
    zech
    0.72
    worldly
    0.72
     assorted
    0.69
    ibrary
    0.69
    sky
    0.69
    ilitarian
    0.67
     things
    0.66
     feats
    0.65
    Activations Density 0.046%

    No Known Activations