© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 3711
    Prev
    Next
    INDEX
    Explanations

    phrases related to the abbreviation "K" followed by a single letter and a number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity represented by the letter 'K'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.90
    ãĥ¼ãĥĨãĤ£
    -0.86
     Marketable
    -0.82
    utics
    -0.69
    ãĥ¼ãĥĨ
    -0.68
    theless
    -0.66
     acknow
    -0.65
     Creed
    -0.63
     constitu
    -0.62
    ãĥ¯
    -0.62
    POSITIVE LOGITS
    won
    1.09
    EEP
    1.07
    oop
    1.03
    avan
    0.99
    ratom
    0.99
    rieg
    0.96
    ernels
    0.95
    essel
    0.94
    etch
    0.93
    ISS
    0.93
    Activations Density 0.039%

    No Known Activations