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. 8-RES-JB
    6. 3694
    Prev
    Next
    INDEX
    Explanations

    tech products and specifications

    oai_token-act-pair · gpt-3.5-turbo

    names and specifications of electronic devices, particularly laptops and smartphones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #$#$
    -0.77
    abama
    -0.73
     metic
    -0.73
    akespeare
    -0.71
    ãĤ±
    -0.69
    arial
    -0.67
    relations
    -0.67
    opathic
    -0.67
    ãĤ©
    -0.66
    asha
    -0.66
    POSITIVE LOGITS
     Plus
    0.90
     Edition
    0.87
     Dimensions
    0.85
     Series
    0.84
     Bundle
    0.83
     XL
    0.82
    âĦ¢
    0.81
     Sandwich
    0.79
     II
    0.78
     variants
    0.76
    Activations Density 0.154%

    No Known Activations