© 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. 10-RES-JB
    11. 11634
    Prev
    Next
    INDEX
    Explanations

    information related to actions and behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to threats or dangers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Provincial
    -0.60
     Farmers
    -0.60
     Izan
    -0.53
    _-
    -0.52
     Towns
    -0.51
    çīĪ
    -0.50
    CONCLUS
    -0.50
     Farmer
    -0.50
    alion
    -0.49
    FontSize
    -0.49
    POSITIVE LOGITS
    versive
    0.68
     inappropriately
    0.64
    pee
    0.64
    limits
    0.63
    their
    0.62
     superflu
    0.61
     excessively
    0.60
    dirty
    0.58
    ouched
    0.58
     undesirable
    0.58
    Activations Density 1.072%

    No Known Activations