© 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. 9-RES-JB
    11. 7279
    Prev
    Next
    INDEX
    Explanations

    discussions or dialogues within documents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "conversation" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elin
    -0.70
     Flavoring
    -0.67
    peria
    -0.66
    ADA
    -0.64
    aye
    -0.64
    rule
    -0.64
    fitting
    -0.64
    iaries
    -0.63
    stri
    -0.61
    zona
    -0.61
    POSITIVE LOGITS
     overheard
    0.99
     conversation
    0.92
     banter
    0.89
    ogue
    0.89
     conversations
    0.83
     between
    0.82
     starter
    0.79
     invitations
    0.79
     about
    0.78
     transcripts
    0.78
    Activations Density 0.062%

    No Known Activations