© 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. 10-RES-JB
    11. 12297
    Prev
    Next
    INDEX
    Explanations

    words related to control or influence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to control or authority over various entities

    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
     Serving
    -0.67
    enegger
    -0.65
    rouse
    -0.65
    geries
    -0.63
     Lect
    -0.60
    igmat
    -0.59
    resso
    -0.58
    GGGGGGGG
    -0.58
     conscientious
    -0.57
     discrep
    -0.57
    POSITIVE LOGITS
     of
    1.01
     thereof
    0.99
    orship
    0.92
    over
    0.85
     over
    0.84
    eering
    0.80
     control
    0.79
    ANCE
    0.78
    ership
    0.77
    ability
    0.76
    Activations Density 0.075%

    No Known Activations