© 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. 20932
    Prev
    Next
    INDEX
    Explanations

    professional job titles related to management and supervision

    oai_token-act-pair · gpt-3.5-turbo

    job titles and positions within organizations

    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
     Attacks
    -0.65
    rav
    -0.64
     Invasion
    -0.60
    rums
    -0.59
     Nightmares
    -0.59
    gotten
    -0.58
    oks
    -0.58
     Dreams
    -0.57
     Beasts
    -0.56
    rought
    -0.56
    POSITIVE LOGITS
     overseeing
    1.09
     liaison
    0.94
     for
    0.92
     advisor
    0.89
     extraord
    0.87
     specializing
    0.87
     aboard
    0.86
    person
    0.85
     supervisor
    0.84
     assistant
    0.83
    Activations Density 0.182%

    No Known Activations