© 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. 19679
    Prev
    Next
    INDEX
    Explanations

    words related to technology and accessories

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "band" and its variations in context

    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
     simultane
    -0.63
    aminer
    -0.61
     frag
    -0.60
     INTO
    -0.59
     STA
    -0.58
     Horror
    -0.57
     Happ
    -0.57
     Nobel
    -0.56
    IDENT
    -0.56
    MAL
    -0.55
    POSITIVE LOGITS
    band
    1.22
    wagon
    1.14
    bands
    1.11
    width
    1.06
    ictionary
    1.03
    ages
    0.93
    camp
    0.93
    Band
    0.92
     bands
    0.91
     band
    0.87
    Activations Density 0.013%

    No Known Activations