© 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. 17194
    Prev
    Next
    INDEX
    Explanations

    items related to food and drink

    oai_token-act-pair · gpt-3.5-turbo

    references to containers or quantities of food and drink

    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
     ancest
    -0.61
     intermedi
    -0.61
     Factors
    -0.60
     entrants
    -0.60
     collusion
    -0.58
     electors
    -0.58
     detrim
    -0.58
    avid
    -0.57
     architects
    -0.56
    poses
    -0.56
    POSITIVE LOGITS
     of
    1.41
     thereof
    1.25
    Of
    1.09
     Of
    1.08
    of
    1.03
     OF
    0.96
    OF
    0.93
    ful
    0.89
    oft
    0.85
    fen
    0.82
    Activations Density 0.304%

    No Known Activations