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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 19123
    Prev
    Next
    INDEX
    Explanations

    financial terms and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to personal computers (PC)

    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
    glers
    -0.76
    ãĥĦ
    -0.75
     Bie
    -0.74
    ãĥĥ
    -0.72
    fulness
    -0.71
     Buc
    -0.71
     Dortmund
    -0.68
     Eisen
    -0.67
    âĸ¬
    -0.66
     Gins
    -0.65
    POSITIVE LOGITS
    PC
    1.40
    rint
    0.95
    ORPG
    0.94
    ombat
    0.93
    ategory
    0.93
    Console
    0.87
    odcast
    0.87
    onduct
    0.86
    etition
    0.84
    Ps
    0.84
    Activations Density 0.005%

    No Known Activations