© 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. 3768
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to video games and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and entities in the context of video game-related discussions

    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
    é¾įå¥ij士
    -1.02
    agents
    -0.82
    circ
    -0.79
     Marketable
    -0.71
    Reviewer
    -0.69
    nown
    -0.67
     sidx
    -0.67
    umbn
    -0.67
    Georg
    -0.67
     huh
    -0.66
    POSITIVE LOGITS
     Lara
    1.41
     Rica
    0.84
    phies
    0.82
    vel
    0.80
    bley
    0.78
    kees
    0.77
    uggage
    0.73
     Cro
    0.72
     Browne
    0.72
    otle
    0.72
    Activations Density 0.011%

    No Known Activations