Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 15705
    Prev
    Next
    INDEX
    Explanations

    references to interviews conducted through various communication methods, such as phone calls or emails

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edia
    -0.81
    Mods
    -0.70
     Regulations
    -0.67
     aven
    -0.66
     Confederate
    -0.66
     inflicting
    -0.63
     wre
    -0.61
     disliked
    -0.61
     Directive
    -0.60
     corpor
    -0.57
    POSITIVE LOGITS
     telephone
    1.07
     interview
    1.05
     phone
    1.03
     Skype
    0.94
     translator
    0.90
     interviewed
    0.84
     interviewer
    0.83
     emailed
    0.79
     interviews
    0.78
     TODAY
    0.78
    Activations Density 0.106%

    No Known Activations