© 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. 10400
    Prev
    Next
    INDEX
    Explanations

    words related to events or occasions where people gather

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "reception" and its variants

    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
    chn
    -0.77
    thin
    -0.69
    chin
    -0.68
    zh
    -0.66
     Sul
    -0.66
    amaz
    -0.64
     mortg
    -0.64
    sol
    -0.61
    mine
    -0.60
    âĵĺ
    -0.60
    POSITIVE LOGITS
     reception
    1.53
    DragonMagazine
    0.93
    alled
    0.92
     receptions
    0.87
    ally
    0.84
    aries
    0.84
    acion
    0.83
    iday
    0.80
    abilia
    0.80
    isson
    0.79
    Activations Density 0.010%

    No Known Activations