© 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. 2-RES-JB
    11. 23909
    Prev
    Next
    INDEX
    Explanations

    mentions of innovative ideas, methods, or technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to innovation and innovative concepts

    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
    phe
    -0.67
    thus
    -0.66
    ferred
    -0.64
     Hume
    -0.64
    nery
    -0.63
    eda
    -0.63
    large
    -0.62
     FAA
    -0.62
    apa
    -0.61
    tha
    -0.60
    POSITIVE LOGITS
     minded
    1.03
     entreprene
    0.93
     innov
    0.86
    minded
    0.82
     innovation
    0.81
     collaborations
    0.79
     innovative
    0.77
    ively
    0.77
    wcs
    0.76
     thinkers
    0.75
    Activations Density 0.014%

    No Known Activations