© 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. 4-RES-JB
    6. 683
    Prev
    Next
    INDEX
    Explanations

    words related to names, titles, and companies starting with "Rel" or "rel"

    oai_token-act-pair · gpt-3.5-turbo

    words related to the term 'relate' and its derivatives

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

    No Comments

    Negative Logits
     Slate
    -0.91
     Mehran
    -0.75
     Archdemon
    -0.70
     Butterfly
    -0.68
    ãģ®éŃĶ
    -0.66
     Lowell
    -0.64
     Featured
    -0.63
    teenth
    -0.62
    åĩ
    -0.62
     Pru
    -0.61
    POSITIVE LOGITS
    aughs
    0.88
    ulous
    0.87
    ciating
    0.86
    heed
    0.82
    ativity
    0.82
    MpServer
    0.79
    ministic
    0.76
    owship
    0.76
    antic
    0.75
    ency
    0.74
    Activations Density 0.048%

    No Known Activations