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. 7-RES-JB
    6. 6103
    Prev
    Next
    INDEX
    Explanations

    information requesting or providing details for contacting authorities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to seeking assistance or reporting information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Average
    -0.68
     billionaires
    -0.66
    ORPG
    -0.63
     millionaire
    -0.62
    ãĤ¦ãĤ¹
    -0.60
     Became
    -0.60
     Barney
    -0.57
    IVES
    -0.57
     Shant
    -0.57
     mansion
    -0.57
    POSITIVE LOGITS
     hesitate
    0.99
     notify
    0.93
     forwarded
    0.91
     answ
    0.88
     Submit
    0.84
    reply
    0.84
     submit
    0.84
    Email
    0.81
     Contact
    0.79
     promptly
    0.78
    Activations Density 0.470%

    No Known Activations