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. 10-RES-JB
    6. 18013
    Prev
    Next
    INDEX
    Explanations

    phrases related to various issues or topics being discussed

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the presence of problems or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascript
    -0.79
    Contents
    -0.77
    odes
    -0.75
    aren
    -0.70
    Explore
    -0.68
    chairs
    -0.66
    soever
    -0.66
     guiActiveUnfocused
    -0.65
    ids
    -0.65
    COMPLE
    -0.63
    POSITIVE LOGITS
     Matter
    0.70
     obligatory
    0.66
     Lav
    0.65
     kicker
    0.64
     Butt
    0.63
     Glac
    0.63
     Mail
    0.61
     Huma
    0.60
     the
    0.60
     Tatt
    0.60
    Activations Density 0.143%

    No Known Activations