© 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. 0-RES-JB
    11. 12330
    Prev
    Next
    INDEX
    Explanations

    words related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ver" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houses
    -0.72
     Throne
    -0.70
     throne
    -0.65
     HQ
    -0.64
    hai
    -0.63
     Ogre
    -0.62
     iPod
    -0.61
     retarded
    -0.60
     rapp
    -0.58
     cake
    -0.57
    POSITIVE LOGITS
    ver
    4.45
    VER
    2.26
    vers
    2.09
    Ver
    1.67
    vered
    1.57
    ving
    1.51
    vert
    1.41
    vier
    1.37
    ved
    1.35
    vant
    1.34
    Activations Density 0.014%

    No Known Activations