© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 23838
    Prev
    Next
    INDEX
    Explanations

    sentences ending with strong punctuation like periods and semicolons

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence structure elements

    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
    Mars
    -0.63
    itialized
    -0.61
    ħĭ
    -0.61
    ueller
    -0.61
    rio
    -0.60
    ãĥĭ
    -0.60
    ML
    -0.59
    Path
    -0.59
     Starr
    -0.58
    omics
    -0.57
    POSITIVE LOGITS
     Traff
    0.67
     respectively
    0.64
     Exper
    0.61
    Downloadha
    0.58
    while
    0.57
     Such
    0.57
    maxwell
    0.57
     beware
    0.56
    instead
    0.56
     Families
    0.55
    Activations Density 1.114%

    No Known Activations