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. 9427
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a continuation or conclusion of a situation

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "After all" as a transition in arguments or points made

    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
     Loft
    -0.62
    rouse
    -0.57
    LR
    -0.56
     simultane
    -0.55
     sep
    -0.55
     skelet
    -0.54
    MX
    -0.54
    /)
    -0.53
     streng
    -0.53
     magnet
    -0.53
    POSITIVE LOGITS
    iances
    0.84
    ying
    0.79
     else
    0.73
    tz
    0.70
    uding
    0.69
    ãĥķãĤ©
    0.68
    ogene
    0.68
    igators
    0.67
    ional
    0.67
    wing
    0.64
    Activations Density 0.021%

    No Known Activations