© 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. 10-RES-JB
    6. 20544
    Prev
    Next
    INDEX
    Explanations

    invalid email addresses

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to email validation and error messaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abouts
    -0.72
    esville
    -0.70
    orks
    -0.69
    leases
    -0.66
    ndum
    -0.65
    mental
    -0.64
    cham
    -0.63
    imer
    -0.62
    arthed
    -0.62
    ¥µ
    -0.62
    POSITIVE LOGITS
     Invalid
    0.78
     invalid
    0.76
     Void
    0.76
     Field
    0.69
     Forbidden
    0.68
     captcha
    0.64
     blank
    0.63
     Valid
    0.62
    email
    0.61
     fields
    0.61
    Activations Density 0.025%

    No Known Activations