© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22695
    Prev
    Next
    INDEX
    Explanations

    terms relating to authority or power

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "control."

    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
    soType
    -0.85
    agher
    -0.80
    eous
    -0.73
    estones
    -0.71
    letter
    -0.67
    artisan
    -0.67
    soDeliveryDate
    -0.65
    jen
    -0.65
    latest
    -0.65
    letters
    -0.65
    POSITIVE LOGITS
     control
    3.79
    control
    3.07
     Control
    2.97
     CONTROL
    2.64
     controls
    2.57
    Control
    2.42
     controlling
    2.15
     controlled
    2.01
     Controls
    1.93
    controlled
    1.73
    Activations Density 0.025%

    No Known Activations