© 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. 12-RES-JB
    11. 4432
    Prev
    Next
    INDEX
    Explanations

    phrases related to behavioral economics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to behavioral and structural dynamics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     âĶľ
    -0.73
    pires
    -0.71
    IUM
    -0.69
    nas
    -0.67
    ocrates
    -0.65
    ACTION
    -0.65
    cone
    -0.62
    rooms
    -0.62
    Woman
    -0.61
    paces
    -0.61
    POSITIVE LOGITS
    ized
    0.99
     changes
    0.89
     weaknesses
    0.87
     change
    0.87
    ised
    0.85
    izational
    0.85
     racism
    0.85
     inertia
    0.83
    izable
    0.82
     factors
    0.80
    Activations Density 0.079%

    No Known Activations