© 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. 20781
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "P" with corresponding numerical identifiers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'P' 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
     Rebels
    -0.87
     diplom
    -0.81
     GOODMAN
    -0.79
    ģĸ
    -0.72
     Orche
    -0.71
     Exodus
    -0.69
     Breaking
    -0.67
     EntityItem
    -0.66
    ãĤ´ãĥ³
    -0.66
     Slov
    -0.65
    POSITIVE LOGITS
    aired
    1.29
    ardon
    1.23
    ivot
    1.19
    airs
    1.17
    ierce
    1.15
    ainted
    1.13
    adding
    1.13
    uls
    1.11
    appy
    1.09
    ussy
    1.08
    Activations Density 0.045%

    No Known Activations