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. 6-RES-JB
    6. 12539
    Prev
    Next
    INDEX
    Explanations

    phone numbers in text

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of identification numbers, particularly phone and license plate numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipation
    -0.79
     contrace
    -0.76
    apers
    -0.74
     benches
    -0.74
    rike
    -0.72
    ulp
    -0.72
    ilib
    -0.72
    ittle
    -0.71
    ersion
    -0.71
    venants
    -0.69
    POSITIVE LOGITS
     identifier
    0.83
     passwords
    0.79
     registration
    0.78
     aliases
    0.78
     belonging
    0.78
     spoof
    0.77
     password
    0.77
     alias
    0.75
    plates
    0.75
     generator
    0.75
    Activations Density 0.102%

    No Known Activations