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. 22075
    Prev
    Next
    INDEX
    Explanations

    sentences with an emphasis on abstract concepts or philosophical musings

    oai_token-act-pair · gpt-3.5-turbo

    concepts of philosophical depth or irony

    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
    dit
    -0.79
    byter
    -0.75
    idem
    -0.75
    tenance
    -0.71
    catentry
    -0.70
    BUS
    -0.70
    MpServer
    -0.69
    KO
    -0.69
    linger
    -0.68
    vice
    -0.66
    POSITIVE LOGITS
     dwelling
    0.72
    tones
    0.70
     watching
    0.69
     Enlightenment
    0.69
     these
    0.68
    effic
    0.67
     THESE
    0.66
     knowing
    0.66
     detecting
    0.65
    adding
    0.65
    Activations Density 0.209%

    No Known Activations