Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22056
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly those related to entertainment or sports

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the name "Josh."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sahara
    -0.72
     jung
    -0.70
    theless
    -0.70
    heit
    -0.69
    ça
    -0.65
     womb
    -0.64
    emies
    -0.63
    vironment
    -0.63
     labyrinth
    -0.63
    sylv
    -0.61
    POSITIVE LOGITS
    iak
    0.82
    ramer
    0.72
    akis
    0.71
    opher
    0.70
    ovsky
    0.69
    offer
    0.66
    henko
    0.65
    ban
    0.65
    Han
    0.65
    iden
    0.65
    Activations Density 0.241%

    No Known Activations