© 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. 20979
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison, evaluation, and critique

    oai_token-act-pair · gpt-3.5-turbo

    negative and positive descriptors related to events or situations

    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
    ADRA
    -0.56
     lett
    -0.56
     conflic
    -0.56
    roit
    -0.55
    blast
    -0.54
     unequ
    -0.51
     warr
    -0.51
    ascript
    -0.50
     Cannot
    -0.49
    liv
    -0.49
    POSITIVE LOGITS
     is
    1.33
     are
    1.09
     was
    1.01
     involves
    0.91
     relates
    0.89
     revolves
    0.84
    is
    0.84
     lies
    0.81
     consists
    0.77
     include
    0.76
    Activations Density 0.674%

    No Known Activations