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. 11-RES-JB
    6. 7399
    Prev
    Next
    INDEX
    Explanations

    phrases related to the way people treat each other

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the treatment and respect of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ongo
    -0.69
    ahime
    -0.68
     linking
    -0.62
    ipl
    -0.62
    allion
    -0.59
    isSpecialOrderable
    -0.58
     Chocobo
    -0.58
     Towns
    -0.58
     Alps
    -0.57
    undo
    -0.57
    POSITIVE LOGITS
     differently
    1.43
     unfairly
    1.21
     harshly
    1.15
     respectfully
    1.12
     kindly
    1.11
     horribly
    1.10
     badly
    1.09
     humane
    1.07
     accordingly
    1.07
     equally
    1.06
    Activations Density 0.158%

    No Known Activations