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. 2706
    Prev
    Next
    INDEX
    Explanations

    sentence-ending periods with high confidence

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    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
    soDeliveryDate
    -0.69
     mosqu
    -0.67
     killers
    -0.60
    arettes
    -0.58
    swick
    -0.56
    FG
    -0.55
     expires
    -0.54
     recite
    -0.54
    Ü
    -0.54
    ÃĥÃĤ
    -0.54
    POSITIVE LOGITS
    dk
    0.65
    notations
    0.65
    np
    0.65
    BBC
    0.64
    mosp
    0.63
    ajor
    0.61
    auri
    0.59
     subp
    0.58
    rots
    0.58
    humans
    0.56
    Activations Density 0.196%

    No Known Activations