© 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. 10-RES-JB
    11. 10524
    Prev
    Next
    INDEX
    Explanations

    names starting with "V" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals with the initial "V"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AAA
    -0.72
     AAP
    -0.68
     Companion
    -0.68
    Downloadha
    -0.67
     Licensed
    -0.66
     pci
    -0.65
     CPC
    -0.65
     DRM
    -0.63
     Rampage
    -0.63
     deduction
    -0.63
    POSITIVE LOGITS
    idal
    1.09
    iera
    1.09
    ito
    1.08
    lah
    1.08
    riend
    1.07
    augh
    1.06
    icious
    1.05
    alk
    1.05
    ulet
    1.04
    incent
    1.03
    Activations Density 0.034%

    No Known Activations