© 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. 4-RES-JB
    11. 4813
    Prev
    Next
    INDEX
    Explanations

    phrases related to a large portion or quantity of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate quantity or proportion

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

    No Comments

    Negative Logits
     recip
    -0.69
    EStream
    -0.69
     confir
    -0.66
     stacks
    -0.65
     DISTRICT
    -0.60
    quit
    -0.59
    TOP
    -0.58
    ħĭ
    -0.57
    bid
    -0.57
    Enh
    -0.57
    POSITIVE LOGITS
     course
    0.79
    course
    0.71
    sky
    0.70
    distance
    0.70
    stay
    0.68
    odor
    0.67
     Nort
    0.66
    ourn
    0.65
    pace
    0.63
     Athletic
    0.62
    Activations Density 0.072%

    No Known Activations