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. 7-RES-JB
    6. 8332
    Prev
    Next
    INDEX
    Explanations

    words or phrases expressing contrast

    oai_token-act-pair · gpt-3.5-turbo

    the word "though," indicating a contrast or exception in the statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enced
    -0.81
     bark
    -0.59
     bip
    -0.58
     Ing
    -0.55
     hurd
    -0.54
     Oakland
    -0.54
    nea
    -0.54
     insensitive
    -0.53
     equival
    -0.53
    ccording
    -0.53
    POSITIVE LOGITS
    AMI
    0.80
     guiActiveUn
    0.79
    itiz
    0.77
    unders
    0.74
    deals
    0.74
    under
    0.73
    OTUS
    0.71
     ;)
    0.66
    fman
    0.65
    ombat
    0.65
    Activations Density 0.129%

    No Known Activations