© 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. 10489
    Prev
    Next
    INDEX
    Explanations

    references to the initials "MV"

    oai_token-act-pair · gpt-3.5-turbo

    the letter "V"

    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
    ãĥ³ãĤ¸
    -0.84
    ãĤ´ãĥ³
    -0.80
    --------------------------------------------------------
    -0.78
    éĹĺ
    -0.78
    ¥µ
    -0.77
    Ú
    -0.68
    manship
    -0.68
    dress
    -0.66
    bender
    -0.66
    ¿½
    -0.66
    POSITIVE LOGITS
    III
    1.29
    ancouver
    1.16
    arsity
    1.09
    ascular
    1.08
    apor
    1.07
    alkyrie
    1.07
    ampire
    1.07
    ideos
    1.05
    isible
    1.04
    odka
    1.04
    Activations Density 0.025%

    No Known Activations