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. 8-RES-JB
    6. 23229
    Prev
    Next
    INDEX
    Explanations

    personal experiences and emotions described in a narrative style

    oai_token-act-pair · gpt-3.5-turbo

    expressions of intense emotions and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FTA
    -0.71
     DEFENSE
    -0.69
     Alternatively
    -0.66
     Additionally
    -0.64
     Seeking
    -0.64
     recommends
    -0.63
     Likewise
    -0.63
     advises
    -0.63
    ospons
    -0.63
    shall
    -0.62
    POSITIVE LOGITS
     unbelievable
    0.94
     unbeliev
    0.82
     really
    0.82
     amaz
    0.82
     freaking
    0.81
     honestly
    0.80
     surreal
    0.79
     unreal
    0.79
     vividly
    0.78
     literally
    0.78
    Activations Density 0.675%

    No Known Activations