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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11398
    Prev
    Next
    INDEX
    Explanations

    adjectives related to describing psychological behaviors and tendencies

    oai_token-act-pair · gpt-3.5-turbo

    themes of addiction and denial in behaviors and societal norms

    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
    sites
    -0.98
    atories
    -0.95
    osponsors
    -0.95
    apers
    -0.87
    hops
    -0.87
    events
    -0.86
    flags
    -0.85
    pages
    -0.83
    aways
    -0.82
    votes
    -0.82
    POSITIVE LOGITS
     fascination
    1.47
     desire
    1.45
     urge
    1.43
     propensity
    1.41
     inability
    1.39
     aversion
    1.37
     belief
    1.37
     tendency
    1.35
     appreciation
    1.34
     inclination
    1.33
    Activations Density 0.304%

    No Known Activations