© 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. 11-RES-JB
    11. 21262
    Prev
    Next
    INDEX
    Explanations

    phrases related to optimism and confidence in future prospects or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    statements reflecting satisfaction or confidence in future outcomes

    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
     censored
    -0.85
     redacted
    -0.76
     censor
    -0.74
     improperly
    -0.74
     coerc
    -0.70
    uphem
    -0.70
    ļéĨĴ
    -0.69
     inconvenient
    -0.68
     mistakenly
    -0.68
    SPONSORED
    -0.67
    POSITIVE LOGITS
     momentum
    1.04
     Expect
    0.90
     things
    0.88
     progress
    0.83
     Velocity
    0.83
     Rebirth
    0.83
     Tomorrow
    0.82
     2018
    0.81
     hopefully
    0.81
     we
    0.81
    Activations Density 0.429%

    No Known Activations