© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20621
    Prev
    Next
    INDEX
    Explanations

    words related to reversibility

    oai_token-act-pair · gpt-3.5-turbo

    words that end in 'vers' or variations of the suffix 'urs' or 'vis'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Soldier
    -0.60
     eminent
    -0.58
     reinforcement
    -0.57
     Dahl
    -0.57
     Gilmore
    -0.55
    ERN
    -0.54
    USD
    -0.53
     partic
    -0.52
     Yemeni
    -0.52
     Columb
    -0.52
    POSITIVE LOGITS
    iveness
    1.57
    ibility
    1.44
    ively
    1.44
    ibilities
    1.40
    ibly
    1.34
    hip
    1.31
    es
    1.28
    ible
    1.28
    ions
    1.26
    ory
    1.23
    Activations Density 0.073%

    No Known Activations