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. 0-RES-JB
    6. 14098
    Prev
    Next
    INDEX
    Explanations

    themes related to social injustice

    oai_token-act-pair · gpt-3.5-turbo

    mention of social injustices and wrongdoing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depend
    -0.81
     depends
    -0.74
     specialized
    -0.69
    mers
    -0.69
    mi
    -0.68
     immune
    -0.67
    mit
    -0.66
    CG
    -0.66
     flexible
    -0.65
    plug
    -0.64
    POSITIVE LOGITS
     injustice
    2.76
     injust
    2.39
     wrongdoing
    2.20
     brutality
    2.17
     atrocities
    2.12
     hypocrisy
    2.03
     atroc
    1.80
     abuses
    1.72
     absurdity
    1.57
     criminality
    1.54
    Activations Density 0.046%

    No Known Activations