© 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 EvalsExportsAPI 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. 7-RES-JB
    11. 24107
    Prev
    Next
    INDEX
    Explanations

    words related to programming or setting particular behaviors and attributes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to programming and conditioning in a biological or artificial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheong
    -0.81
     Sack
    -0.79
    fal
    -0.77
    Scotland
    -0.76
    apest
    -0.69
    apers
    -0.65
    iversary
    -0.65
    asta
    -0.64
     umbrella
    -0.63
     Hague
    -0.63
    POSITIVE LOGITS
    eering
    0.88
     Reloaded
    0.82
     instincts
    0.81
    strap
    0.77
    washed
    0.75
    eer
    0.74
     bred
    0.72
    ependent
    0.70
     instinct
    0.70
     algorithms
    0.68
    Activations Density 0.139%

    No Known Activations