© 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. 2018
    Prev
    Next
    INDEX
    Explanations

    items of communication-related significance, such as email sign-ups and newsletters

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    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
     acquaintance
    -0.69
     hood
    -0.69
     cod
    -0.68
    fman
    -0.68
     oun
    -0.68
     smoked
    -0.66
     hom
    -0.66
     altar
    -0.66
     reversible
    -0.65
     enumer
    -0.65
    POSITIVE LOGITS
     Subscribe
    1.02
     Please
    0.91
     Want
    0.90
    push
    0.89
    letters
    0.89
     Each
    0.88
     Readers
    0.87
    avanaugh
    0.86
     Its
    0.85
     Visit
    0.84
    Activations Density 0.196%

    No Known Activations