© 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. 7-RES-JB
    11. 23094
    Prev
    Next
    INDEX
    Explanations

    calls to action for newsletter sign-ups

    oai_token-act-pair · gpt-3.5-turbo

    instances of newsletter-related actions or prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.76
    »Ĵ
    -0.72
     heel
    -0.72
    rency
    -0.62
     carp
    -0.61
    ,,,,
    -0.61
    rology
    -0.61
    EStreamFrame
    -0.59
     elim
    -0.58
     interf
    -0.57
    POSITIVE LOGITS
     WATCHED
    0.79
     Email
    0.75
     Thumbnails
    0.74
     Picks
    0.67
     Emails
    0.66
    irmation
    0.66
    encrypted
    0.65
    advertisement
    0.64
     Login
    0.64
    icker
    0.63
    Activations Density 0.021%

    No Known Activations