© 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. 2-RES-JB
    6. 18480
    Prev
    Next
    INDEX
    Explanations

    email addresses with gmail domains

    oai_token-act-pair · gpt-3.5-turbo

    email addresses and domain names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.69
    tein
    -0.65
    eating
    -0.64
    earable
    -0.64
    TAIN
    -0.63
     plaintiff
    -0.62
    authorized
    -0.62
     Franch
    -0.60
     prost
    -0.59
    Recomm
    -0.59
    POSITIVE LOGITS
    gmail
    1.12
    yahoo
    0.89
    ileaks
    0.83
    apest
    0.78
    email
    0.75
    fp
    0.70
    orthern
    0.69
    zsche
    0.68
     msg
    0.67
    legram
    0.66
    Activations Density 0.011%

    No Known Activations