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. 0-RES-JB
    6. 24148
    Prev
    Next
    INDEX
    Explanations

    references to logs or records, particularly those related to communication or tracking

    oai_token-act-pair · gpt-3.5-turbo

    references to chat logs or records of online activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gene
    -0.72
     Aff
    -0.69
    universal
    -0.69
    gie
    -0.65
    ashion
    -0.65
     Creative
    -0.64
    orio
    -0.63
     Variant
    -0.63
     Dhabi
    -0.62
     universal
    -0.61
    POSITIVE LOGITS
     logs
    3.93
     log
    1.57
     logging
    1.47
     logged
    1.44
     dumps
    1.39
     caches
    1.38
     records
    1.36
     Log
    1.27
     streams
    1.22
    Log
    1.22
    Activations Density 0.005%

    No Known Activations