© 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. 24431
    Prev
    Next
    INDEX
    Explanations

    references to a specific acronym (FC)

    oai_token-act-pair · gpt-3.5-turbo

    references to facilitated communication

    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
    Downloadha
    -0.70
     Carmen
    -0.70
     Dru
    -0.68
    lihood
    -0.66
     Gry
    -0.65
     è£ıè¦ļéĨĴ
    -0.64
     Berk
    -0.63
     heck
    -0.62
     Ples
    -0.62
    strument
    -0.61
    POSITIVE LOGITS
    urrent
    0.91
    ombo
    0.87
    ranch
    0.87
    asting
    0.87
    ruits
    0.85
    urry
    0.84
    ORD
    0.82
    emetery
    0.80
    ORE
    0.80
    actory
    0.80
    Activations Density 0.008%

    No Known Activations