© 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. 20795
    Prev
    Next
    INDEX
    Explanations

    phrases related to technological features, interventions, or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    words related to media, broadcasting, and processes

    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
    姫
    -0.80
    SOURCE
    -0.72
    TEXTURE
    -0.67
    POSE
    -0.59
    FINE
    -0.58
    uddin
    -0.56
    DK
    -0.55
     msec
    -0.55
     Sharif
    -0.54
     Instr
    -0.54
    POSITIVE LOGITS
    ioned
    1.01
    lessly
    0.98
    matically
    0.93
    ciation
    0.88
    lete
    0.85
    ership
    0.84
    nels
    0.83
    naire
    0.81
    marked
    0.80
    ings
    0.78
    Activations Density 0.654%

    No Known Activations