© 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. 7545
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various entities such as people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    specific references to locations, notable events, or prominent figures in various contexts

    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
    aeda
    -0.61
    docker
    -0.61
    tnc
    -0.58
     theirs
    -0.55
    orney
    -0.53
    plementation
    -0.53
     throne
    -0.53
    >>\
    -0.52
    aterasu
    -0.51
     hers
    -0.51
    POSITIVE LOGITS
     âľ
    0.60
    Hor
    0.59
    cknowled
    0.59
     Files
    0.58
     Votes
    0.57
    imil
    0.57
    Wire
    0.56
     Report
    0.56
     (@
    0.55
     Stats
    0.54
    Activations Density 0.544%

    No Known Activations