© 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. 7-RES-JB
    11. 8818
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    oai_token-act-pair · gpt-3.5-turbo

    sequences of punctuation and conjunctions that suggest complex sentence structures

    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
    zar
    -0.69
    culosis
    -0.68
    rotein
    -0.68
    abase
    -0.67
    POST
    -0.67
    apache
    -0.65
    rina
    -0.64
    ItemTracker
    -0.62
     Founding
    -0.61
    wordpress
    -0.60
    POSITIVE LOGITS
    depending
    1.63
     respectively
    1.43
     depending
    1.28
     alike
    0.95
     whichever
    0.93
     ILCS
    0.84
     inclusive
    0.75
     Directions
    0.70
    whatever
    0.68
     Streets
    0.66
    Activations Density 0.413%

    No Known Activations