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. 3-RES-JB
    6. 18668
    Prev
    Next
    INDEX
    Explanations

    phone-related activities or interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to phone communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rix
    -0.91
     Inher
    -0.74
    urities
    -0.70
    issue
    -0.69
     Dresden
    -0.65
     Gibraltar
    -0.65
     DPR
    -0.63
    alid
    -0.63
     Pilgrim
    -0.63
     Weston
    -0.63
    POSITIVE LOGITS
    ysis
    1.04
     phones
    0.95
    phones
    0.92
     phone
    0.85
     handset
    0.82
     booths
    0.81
    gap
    0.78
     contacts
    0.78
    pei
    0.76
     booth
    0.75
    Activations Density 0.019%

    No Known Activations