© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16143
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific substance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sal" in various contexts

    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
     Dominion
    -0.87
    STEP
    -0.80
    lihood
    -0.78
     Breed
    -0.73
     Breaker
    -0.70
    STRUCT
    -0.68
     Sets
    -0.68
     Blessed
    -0.67
    schild
    -0.67
     Annotations
    -0.67
    POSITIVE LOGITS
    utations
    1.10
    mone
    1.03
    udos
    0.95
    isbury
    0.95
    acious
    0.95
    ient
    0.94
    aunch
    0.94
    utation
    0.93
    iency
    0.92
    istry
    0.92
    Activations Density 0.007%

    No Known Activations