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. 6-RES-JB
    6. 23553
    Prev
    Next
    INDEX
    Explanations

    numbers or numerical patterns that are repeated across different sections of the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the number nine or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itable
    -0.75
    itably
    -0.73
    iator
    -0.71
    iated
    -0.70
     Lauder
    -0.70
    ivari
    -0.68
    iating
    -0.67
    escription
    -0.66
     Ukrain
    -0.65
     bleach
    -0.65
    POSITIVE LOGITS
    9999
    1.30
    999
    1.26
    090
    1.17
    06
    1.17
    07
    1.12
    08
    1.09
    04
    1.08
    03
    1.06
    09
    1.04
    NEWS
    0.99
    Activations Density 0.059%

    No Known Activations