© 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. 10671
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific band named "Band"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Band" and its variations in the context of entertainment or performances

    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
    mberg
    -0.72
     Pradesh
    -0.67
    ocrin
    -0.65
    nces
    -0.63
    issance
    -0.62
    sbm
    -0.62
    uper
    -0.61
    bably
    -0.61
    perse
    -0.61
    zanne
    -0.59
    POSITIVE LOGITS
    wagon
    1.06
    Band
    1.02
    width
    0.97
    camp
    0.97
     Band
    0.94
    ictionary
    0.90
    abase
    0.84
    anas
    0.84
    leader
    0.82
    wana
    0.81
    Activations Density 0.009%

    No Known Activations