© 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. 2-RES-JB
    11. 21667
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical compounds

    oai_token-act-pair · gpt-3.5-turbo

    words related to minerals and their classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.67
    inances
    -0.62
    iston
    -0.62
    PLA
    -0.62
    endon
    -0.60
    rompt
    -0.60
    Fla
    -0.60
     Realm
    -0.59
    Liter
    -0.56
    perature
    -0.56
    POSITIVE LOGITS
    hift
    1.13
    terday
    1.02
    ilver
    0.93
    peak
    0.84
    rencies
    0.83
    heet
    0.80
    milo
    0.79
    atable
    0.79
    rers
    0.78
    hips
    0.77
    Activations Density 0.032%

    No Known Activations