© 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. 20021
    Prev
    Next
    INDEX
    Explanations

    words related to causing or bringing about something, often with a negative connotation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "induce" and its variations in contexts related to causing effects or conditions

    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
    rast
    -0.74
    bris
    -0.74
    aunch
    -0.73
     Trash
    -0.72
     Runes
    -0.70
    CLOSE
    -0.69
    priority
    -0.69
    VG
    -0.69
     Blades
    -0.67
    yards
    -0.67
    POSITIVE LOGITS
     induced
    3.30
     induce
    2.86
     inducing
    2.79
     induces
    2.19
     induction
    1.84
     elicit
    1.67
     elic
    1.49
     indu
    1.42
     stimulated
    1.34
     coer
    1.32
    Activations Density 0.039%

    No Known Activations