© 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. 1-RES-JB
    11. 6877
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "primer," which can refer to an introductory book or essential information

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "prime" or "priming"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.89
    INESS
    -0.76
    aved
    -0.74
    icago
    -0.72
    IELD
    -0.68
    olson
    -0.68
    TPS
    -0.66
    oping
    -0.65
    upon
    -0.65
    åŃIJ
    -0.64
    POSITIVE LOGITS
     Prim
    1.36
    itives
    1.13
    itive
    1.08
    prim
    1.05
    Prim
    0.89
    archs
    0.88
    atis
    0.81
     Tarant
    0.80
     Primal
    0.79
     Vict
    0.78
    Activations Density 0.005%

    No Known Activations