Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 10689
    Prev
    Next
    INDEX
    Explanations

    expressions related to being honored or pleased

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing privilege, excitement, and the act of being in a role or position

    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
    orage
    -0.67
    agers
    -0.66
     wills
    -0.65
    uyomi
    -0.65
    é¾
    -0.61
     doct
    -0.60
    è¯
    -0.60
     fid
    -0.59
    atus
    -0.59
    atio
    -0.57
    POSITIVE LOGITS
     Sack
    0.66
     privileged
    0.63
    ttes
    0.63
    noon
    0.62
     CK
    0.62
    reen
    0.61
    agos
    0.59
    Reloaded
    0.59
    clus
    0.58
    Ͻ
    0.58
    Activations Density 0.131%

    No Known Activations