© 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. 0-RES-JB
    11. 4200
    Prev
    Next
    INDEX
    Explanations

    terms related to remote or autonomous control

    oai_token-act-pair · gpt-3.5-turbo

    references to control and dominance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     debut
    -0.76
     Katrina
    -0.74
     embed
    -0.72
     embro
    -0.68
     er
    -0.67
     pee
    -0.67
     essay
    -0.67
     award
    -0.65
     ink
    -0.65
     fruits
    -0.64
    POSITIVE LOGITS
    controlled
    3.84
     controlled
    1.94
    control
    1.90
     Controlled
    1.81
    operated
    1.60
    held
    1.54
    dominated
    1.39
    managed
    1.31
    protected
    1.31
    Control
    1.31
    Activations Density 0.017%

    No Known Activations