© 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. 3-RES-JB
    6. 12255
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers mixed with special characters

    oai_token-act-pair · gpt-3.5-turbo

    characteristic patterns or structures often associated with technical data or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paio
    -0.44
     Flavoring
    -0.41
     minds
    -0.39
     relaxing
    -0.38
    hement
    -0.37
     Garry
    -0.36
     Reloaded
    -0.35
     behavi
    -0.35
     ACTIONS
    -0.34
     citiz
    -0.34
    POSITIVE LOGITS
    _
    0.49
    rc
    0.49
    du
    0.46
    rb
    0.45
    bin
    0.44
    __
    0.43
    powder
    0.42
    callback
    0.42
    tag
    0.41
    df
    0.40
    Activations Density 0.948%

    No Known Activations