© 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. 2312
    Prev
    Next
    INDEX
    Explanations

    names or terms with a specific pattern - specifically those ending in 'p' followed by a digit

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'p'

    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
    æ©Ł
    -0.81
     warr
    -0.75
     GOODMAN
    -0.72
     Leilan
    -0.72
    NESS
    -0.70
     GEAR
    -0.67
     Lauder
    -0.67
     Grateful
    -0.66
    FTWARE
    -0.66
     Palest
    -0.66
    POSITIVE LOGITS
    resents
    1.32
    ossible
    1.28
    airs
    1.26
    ulse
    1.25
    redict
    1.25
    ilot
    1.23
    ossession
    1.21
    aired
    1.19
    ushing
    1.17
    ussy
    1.15
    Activations Density 0.033%

    No Known Activations