© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 13425
    Prev
    Next
    INDEX
    Explanations

    words related to self-discipline and self-regulation

    oai_token-act-pair · gpt-3.5-turbo

    negative self-related concepts and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dug
    -0.71
     Ashe
    -0.70
     BB
    -0.69
    ulhu
    -0.69
     Chains
    -0.68
     Springs
    -0.67
     Baton
    -0.67
     Rath
    -0.67
     Paste
    -0.66
     Hutch
    -0.65
    POSITIVE LOGITS
    esteem
    1.42
    confidence
    1.30
    awareness
    1.28
    expression
    1.27
    determination
    1.27
    defense
    1.26
    righteous
    1.25
    proclaimed
    1.24
    interest
    1.20
    conscious
    1.19
    Activations Density 0.020%

    No Known Activations