© 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. 11917
    Prev
    Next
    INDEX
    Explanations

    terms related to detailed and intricate descriptions or elements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to complexity and delicacy

    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
     face
    -0.61
     shoulder
    -0.60
     squared
    -0.59
    Connector
    -0.59
    LIST
    -0.58
     Kane
    -0.57
     Panther
    -0.57
     Devil
    -0.57
     Shepard
    -0.56
     employee
    -0.56
    POSITIVE LOGITS
    ately
    2.25
    acies
    2.25
    acy
    1.98
    iously
    1.56
    ates
    1.52
    ate
    1.37
    ACY
    1.36
    atism
    1.32
    ature
    1.31
    atures
    1.29
    Activations Density 0.066%

    No Known Activations