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. 0-RES-JB
    6. 20863
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters, particularly the character 'è¡'

    oai_token-act-pair · gpt-3.5-turbo

    non-standard characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittal
    -0.81
    ategory
    -0.76
    ivia
    -0.74
    htaking
    -0.69
    itol
    -0.68
    orthy
    -0.68
    izabeth
    -0.68
     ounce
    -0.67
    kees
    -0.66
    strous
    -0.66
    POSITIVE LOGITS
     Coffee
    0.76
    76561
    0.72
    Dial
    0.71
     coffee
    0.71
    Fire
    0.69
    Rew
    0.67
    Champ
    0.67
    åĤ
    0.62
    RAW
    0.61
    1945
    0.60
    Activations Density 0.000%

    No Known Activations