© 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. 24036
    Prev
    Next
    INDEX
    Explanations

    specific nouns related to purchasing or acquiring items

    oai_token-act-pair · gpt-3.5-turbo

    references to purchasing actions

    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
    xual
    -0.95
    ilial
    -0.79
    ulty
    -0.77
    hematically
    -0.72
    ngth
    -0.72
    ĸļ
    -0.71
    aucuses
    -0.71
    ilic
    -0.68
    amination
    -0.68
    ensable
    -0.67
    POSITIVE LOGITS
     groceries
    1.14
     cheapest
    1.01
     tickets
    0.97
     discounted
    0.96
     cheap
    0.91
     Tickets
    0.89
     pricey
    0.86
     cheaply
    0.86
     cheaper
    0.83
     licences
    0.83
    Activations Density 0.234%

    No Known Activations