© 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. 4-RES-JB
    11. 3661
    Prev
    Next
    INDEX
    Explanations

    verbs related to control or authority

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "command."

    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
    OHN
    -0.70
     Bloom
    -0.66
     Happ
    -0.65
    Rub
    -0.64
     hurd
    -0.62
    Mini
    -0.62
     Hazel
    -0.62
     Roof
    -0.60
     è£ıè
    -0.60
    quickShipAvailable
    -0.60
    POSITIVE LOGITS
    eering
    1.23
    eer
    1.03
    eers
    1.00
    aining
    0.98
    ained
    0.89
     commanded
    0.87
     commands
    0.85
     commanding
    0.84
    ments
    0.84
    ment
    0.83
    Activations Density 0.009%

    No Known Activations