© 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. 2184
    Prev
    Next
    INDEX
    Explanations

    words related to caverns and underground spaces

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "vern" related to various contexts

    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
     HRC
    -0.67
     handlers
    -0.66
     cut
    -0.65
     trans
    -0.65
     interference
    -0.64
     molecule
    -0.64
     delegates
    -0.64
     peanuts
    -0.63
     ple
    -0.63
     donor
    -0.63
    POSITIVE LOGITS
    vern
    4.89
     Vern
    1.34
    clair
    1.10
    ften
    1.08
    vers
    1.07
    veland
    1.03
    ngth
    1.01
    VER
    0.99
    ver
    0.99
    ven
    0.98
    Activations Density 0.008%

    No Known Activations