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. 9-RES-JB
    6. 16902
    Prev
    Next
    INDEX
    Explanations

    names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names of individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onet
    -0.85
    DragonMagazine
    -0.75
    ntil
    -0.64
    raints
    -0.63
    ocious
    -0.63
    geries
    -0.62
    :]
    -0.62
    arp
    -0.62
    amping
    -0.61
    ardless
    -0.61
    POSITIVE LOGITS
     deems
    1.26
     deem
    1.03
     sorely
    0.92
     excel
    0.91
     considers
    0.86
     cove
    0.85
     describes
    0.85
     desperately
    0.82
     undertook
    0.82
     forgot
    0.81
    Activations Density 0.307%

    No Known Activations