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. 10-RES-JB
    6. 11849
    Prev
    Next
    INDEX
    Explanations

    phrases containing speech-related words or direct quotes

    oai_token-act-pair · gpt-3.5-turbo

    instances of expressive or emotionally charged dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artifacts
    -0.89
    issance
    -0.84
    olicy
    -0.82
    emis
    -0.79
    profits
    -0.76
    ropolis
    -0.76
    cair
    -0.75
    hesda
    -0.75
    etheless
    -0.74
    dates
    -0.74
    POSITIVE LOGITS
     whisper
    1.17
     understatement
    1.17
     voice
    1.16
     loud
    1.14
     plaint
    1.12
     tone
    1.12
     tones
    1.10
     sarcastic
    1.09
     chorus
    1.06
     tongue
    1.05
    Activations Density 0.173%

    No Known Activations