© 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. 0-RES-JB
    11. 13594
    Prev
    Next
    INDEX
    Explanations

    text related to research subjects and experiments

    oai_token-act-pair · gpt-3.5-turbo

    references to subjects involved in experiments or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oco
    -0.73
    ame
    -0.70
    ruction
    -0.69
    Coach
    -0.68
    coord
    -0.68
     Coach
    -0.66
    GY
    -0.65
    Lock
    -0.64
    way
    -0.64
    hash
    -0.63
    POSITIVE LOGITS
     subjects
    3.92
     Subjects
    3.04
     subject
    2.25
    subject
    2.03
     topics
    1.92
    Subject
    1.75
     Subject
    1.68
     participants
    1.52
     topic
    1.34
     recipients
    1.19
    Activations Density 0.007%

    No Known Activations