© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 9192
    Prev
    Next
    INDEX
    Explanations

    expletives and violent phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and explicit language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itton
    -0.63
    ————
    -0.62
     downhill
    -0.60
     dracon
    -0.59
     sleeper
    -0.58
    issance
    -0.56
     cooperative
    -0.56
     SERVICE
    -0.56
    FTWARE
    -0.56
    ples
    -0.55
    POSITIVE LOGITS
    ers
    1.35
    ings
    1.24
    enger
    1.08
    ingly
    1.06
    engers
    0.99
    ername
    0.98
    estone
    0.98
    switch
    0.98
    athon
    0.97
    adelphia
    0.96
    Activations Density 0.091%

    No Known Activations