© 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. 9-RES-JB
    11. 13428
    Prev
    Next
    INDEX
    Explanations

    phrases related to email subscriptions and online forms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of email-related requests or mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ---------
    -0.71
    Reply
    -0.61
     stray
    -0.58
     gram
    -0.57
    iter
    -0.56
     misunderstand
    -0.55
     foreground
    -0.53
     misinterpret
    -0.53
    latest
    -0.53
     rehearsal
    -0.53
    POSITIVE LOGITS
     {*
    0.77
    aunders
    0.76
    uct
    0.67
    ħĭ
    0.67
    urchase
    0.66
    pload
    0.64
    settings
    0.63
    gdala
    0.62
    ickets
    0.62
    auder
    0.62
    Activations Density 0.039%

    No Known Activations