© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 7299
    Prev
    Next
    INDEX
    Explanations

    phone numbers with varying formats

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numerical values and associated identifiers, likely related to contact information or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rive
    -0.60
    retty
    -0.59
     draw
    -0.56
     horizont
    -0.55
     ticking
    -0.53
     glued
    -0.52
     hearty
    -0.52
     snowball
    -0.51
     unsurprisingly
    -0.51
     photographic
    -0.51
    POSITIVE LOGITS
    tenance
    0.73
    86
    0.72
    -+-+
    0.72
    89
    0.71
    477
    0.69
    443
    0.68
    88
    0.68
    677
    0.68
    886
    0.67
    663
    0.66
    Activations Density 0.060%

    No Known Activations