© 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. 4-RES-JB
    6. 16489
    Prev
    Next
    INDEX
    Explanations

    invalid or valid email addresses

    oai_token-act-pair · gpt-3.5-turbo

    references to email addresses and issues related to email subscriptions

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

    No Comments

    Negative Logits
    abouts
    -0.85
    icles
    -0.72
    cil
    -0.71
    Sharp
    -0.70
    iak
    -0.69
    laus
    -0.67
    thood
    -0.67
    UF
    -0.66
    ETF
    -0.66
    hma
    -0.66
    POSITIVE LOGITS
     inbox
    1.06
     address
    0.91
     email
    0.88
    antha
    0.88
     sender
    0.86
    email
    0.84
     notification
    0.84
     invitation
    0.81
     alerts
    0.80
    legram
    0.78
    Activations Density 0.021%

    No Known Activations