© 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. 7-RES-JB
    11. 3612
    Prev
    Next
    INDEX
    Explanations

    terms related to "next-generation" technology advancements

    oai_token-act-pair · gpt-3.5-turbo

    references to "next-generation" concepts or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pengu
    -0.74
     Vaughn
    -0.73
    ouf
    -0.72
     Cah
    -0.66
     istg
    -0.64
    ucci
    -0.63
     curls
    -0.62
     Duo
    -0.62
     Burnett
    -0.62
    UAL
    -0.62
    POSITIVE LOGITS
    generation
    1.16
    interstitial
    1.13
    sized
    1.09
    grade
    1.03
    minded
    0.99
    hitting
    0.96
    thinking
    0.96
    to
    0.95
    night
    0.95
    door
    0.94
    Activations Density 0.074%

    No Known Activations