© 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. 9-RES-JB
    11. 7210
    Prev
    Next
    INDEX
    Explanations

    instances where the word "change" is mentioned, often associated with modifying something specific

    oai_token-act-pair · gpt-3.5-turbo

    references to significant changes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.83
    ccoli
    -0.77
    HAEL
    -0.76
    lee
    -0.76
    mith
    -0.73
    lees
    -0.72
    seekers
    -0.70
    cules
    -0.70
    ESE
    -0.69
     alone
    -0.69
    POSITIVE LOGITS
     wording
    1.24
     definition
    1.09
     equation
    1.06
     way
    1.06
     entire
    1.03
     entirety
    1.02
     timeline
    1.02
     trajectory
    1.02
     slightest
    1.01
     parameters
    0.96
    Activations Density 0.225%

    No Known Activations