© 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. 14064
    Prev
    Next
    INDEX
    Explanations

    details related to people's names and roles or titles in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas within text

    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
    andowski
    -0.76
     guiActiveUn
    -0.75
    arge
    -0.73
    erg
    -0.71
    ources
    -0.71
    zers
    -0.71
    ieri
    -0.71
    obin
    -0.69
    uture
    -0.69
    iners
    -0.69
    POSITIVE LOGITS
     etc
    1.03
    76561
    0.79
     Mehran
    0.70
     Sands
    0.68
     Univ
    0.66
     Cameroon
    0.66
     Polo
    0.65
     Kinnikuman
    0.65
     Sor
    0.65
     ISBN
    0.64
    Activations Density 0.240%

    No Known Activations