© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 14933
    Prev
    Next
    INDEX
    Explanations

    personal reflections and opinions indicated by phrases starting with "what struck me", "worries me", "worried me", and "amazes me"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and concerns

    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
     Equality
    -0.79
     Pastebin
    -0.79
    illary
    -0.74
     Publication
    -0.66
     confidentiality
    -0.65
    clusive
    -0.62
     Guid
    -0.60
    ftime
    -0.59
     Prepar
    -0.59
    =~
    -0.58
    POSITIVE LOGITS
     personally
    0.94
    lees
    0.86
     intellectually
    0.81
     irresist
    0.77
     profoundly
    0.75
     sights
    0.74
     psychologically
    0.73
     amaz
    0.72
     vividly
    0.69
     enormously
    0.69
    Activations Density 0.119%

    No Known Activations