© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 10842
    Prev
    Next
    INDEX
    Explanations

    URLs ending with '/' in tweets

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web addresses

    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
     leases
    -0.66
     Restaur
    -0.64
     Reasons
    -0.63
    paio
    -0.62
     primates
    -0.62
     reasons
    -0.62
     Languages
    -0.61
     indications
    -0.61
     advances
    -0.61
     restrooms
    -0.60
    POSITIVE LOGITS
    gallery
    1.00
    hash
    0.95
    fw
    0.91
    dp
    0.88
    oa
    0.87
    tw
    0.83
    detail
    0.83
    dj
    0.83
    embed
    0.82
    cn
    0.82
    Activations Density 0.021%

    No Known Activations