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. 1-RES-JB
    6. 5944
    Prev
    Next
    INDEX
    Explanations

    words related to buying or purchasing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the root "bu," particularly in relation to buying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ALE
    -0.77
     Integrity
    -0.75
     Scand
    -0.73
     Talent
    -0.69
     Cosponsors
    -0.68
     Halls
    -0.65
    */(
    -0.64
     HOR
    -0.64
    croft
    -0.64
     Europa
    -0.64
    POSITIVE LOGITS
    isine
    1.13
    selage
    1.10
    undai
    1.06
    kered
    1.02
    ying
    0.98
    bu
    0.97
    pless
    0.92
    pped
    0.92
    querque
    0.89
    hei
    0.88
    Activations Density 0.006%

    No Known Activations