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. 11-RES-JB
    6. 8123
    Prev
    Next
    INDEX
    Explanations

    numeric values matching a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number 5 or phrases involving the number 5

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hort
    -0.69
    lycer
    -0.65
    worldly
    -0.63
    swick
    -0.63
    swer
    -0.58
    xual
    -0.58
     careful
    -0.58
     tradem
    -0.57
    alions
    -0.57
    velt
    -0.56
    POSITIVE LOGITS
    Thirty
    1.17
    pb
    0.94
    th
    0.92
    678
    0.89
    41
    0.87
    0000
    0.86
    43
    0.83
    69
    0.82
    42
    0.81
    47
    0.81
    Activations Density 0.168%

    No Known Activations