© 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. 11-RES-JB
    6. 21376
    Prev
    Next
    INDEX
    Explanations

    the phrase "going to" with different accompanying words or numbers associated with uncertainty or avoidance

    oai_token-act-pair · gpt-3.5-turbo

    expressions of reluctance or hesitance about discussing certain topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Compass
    -0.81
    owship
    -0.79
    alties
    -0.75
    wick
    -0.72
     Houses
    -0.67
     Reborn
    -0.67
    effects
    -0.67
     Rooms
    -0.66
    knit
    -0.65
     Opportun
    -0.64
    POSITIVE LOGITS
     spoil
    1.27
     exagger
    1.17
     rant
    1.05
     nit
    1.05
     pretend
    1.04
     dwell
    1.03
     speculate
    1.02
     dispar
    0.99
     exaggeration
    0.98
     understatement
    0.97
    Activations Density 0.123%

    No Known Activations