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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21623
    Prev
    Next
    INDEX
    Explanations

    the number "Four" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    the numeral "four" 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 @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idence
    -0.71
     Rica
    -0.67
    UGE
    -0.65
    UTION
    -0.63
    Fed
    -0.63
     Happ
    -0.62
    imei
    -0.62
    AMI
    -0.61
    LER
    -0.60
    igation
    -0.59
    POSITIVE LOGITS
    teenth
    1.91
    teen
    1.90
    eenth
    1.17
    some
    1.16
    een
    1.07
     hundred
    1.06
    square
    1.03
    aciously
    1.01
    fold
    0.94
    acious
    0.91
    Activations Density 0.038%

    No Known Activations