© 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. 12659
    Prev
    Next
    INDEX
    Explanations

    descriptions of people's ages

    oai_token-act-pair · gpt-3.5-turbo

    the presence of unique contextual markers or specific formatting

    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
    _.
    -0.79
    *.
    -0.67
     destro
    -0.66
     agre
    -0.65
     behavi
    -0.65
    emale
    -0.64
     behav
    -0.64
     ;)
    -0.64
     occas
    -0.64
    (*
    -0.63
    POSITIVE LOGITS
     NASCAR
    0.60
     Hillary
    0.60
     Corbyn
    0.59
     Pokémon
    0.58
     Houth
    0.56
     Labour
    0.56
     Nintendo
    0.54
    zbollah
    0.54
     Brewers
    0.54
     Shin
    0.54
    Activations Density 1.830%

    No Known Activations