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. 17386
    Prev
    Next
    INDEX
    Explanations

    company names, specifically related to the telecommunications industry

    oai_token-act-pair · gpt-3.5-turbo

    references to the company "Sprint"

    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
     fet
    -0.73
     Kubrick
    -0.69
     Boyle
    -0.68
     bitters
    -0.64
    âĿ
    -0.63
    emis
    -0.63
     Younger
    -0.61
    orescent
    -0.60
     Luthor
    -0.58
     Ple
    -0.57
    POSITIVE LOGITS
     Sprint
    1.07
    DAQ
    0.91
    Mobile
    0.83
    SQL
    0.82
    rats
    0.79
    ularity
    0.77
    oute
    0.73
    oleon
    0.71
     Unlimited
    0.70
     Mobility
    0.69
    Activations Density 0.009%

    No Known Activations