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. 11-RES-JB
    6. 8745
    Prev
    Next
    INDEX
    Explanations

    words related to buying or selling products or services

    oai_token-act-pair · gpt-3.5-turbo

    references to transactions, selling, and related actions or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ANGE
    -0.69
    inas
    -0.66
    dding
    -0.61
    natureconservancy
    -0.58
    uren
    -0.58
    osi
    -0.57
    ãĥķãĤ¡
    -0.54
    æĺ¯
    -0.53
    retty
    -0.52
    idence
    -0.52
    POSITIVE LOGITS
     to
    1.18
     unto
    1.07
     thereto
    0.94
    to
    0.88
     onto
    0.83
     cheaply
    0.82
     freely
    0.81
     anonymously
    0.81
     orally
    0.78
     TO
    0.77
    Activations Density 0.363%

    No Known Activations