© 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. 19806
    Prev
    Next
    INDEX
    Explanations

    words related to compression or compound words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word related to compounding or combining elements

    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
    FORE
    -0.80
    soever
    -0.67
     Millennium
    -0.66
    \\\\\\\\\\\\\\\\
    -0.65
     Lans
    -0.65
     Rabbit
    -0.63
    576
    -0.62
     Borough
    -0.61
    loo
    -0.61
     Lumpur
    -0.61
    POSITIVE LOGITS
    endium
    1.36
    ulsive
    1.22
    artments
    1.17
    ilers
    1.12
    rehens
    1.11
    acts
    1.06
    ressing
    1.03
    ounding
    1.02
    actor
    0.97
    onential
    0.95
    Activations Density 0.008%

    No Known Activations