© 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. 4401
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names ending with 'b'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter sequence "b"

    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
     nomine
    -0.65
    æ©Ł
    -0.65
     Lauder
    -0.64
     FANTASY
    -0.61
     Gutenberg
    -0.59
    ãĥ´ãĤ¡
    -0.59
     Porsche
    -0.58
    DEM
    -0.58
     essence
    -0.58
    Magikarp
    -0.58
    POSITIVE LOGITS
    rief
    1.33
    odies
    1.19
    attery
    1.14
    ruary
    1.10
    anned
    1.08
    reath
    1.06
    amboo
    1.05
    unker
    1.05
    rows
    1.04
    ibli
    1.03
    Activations Density 0.042%

    No Known Activations