© 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. 11-RES-JB
    6. 9447
    Prev
    Next
    INDEX
    Explanations

    words related to multiculturalism or diversity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to multiplicity and multidimensionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pounding
    -0.61
     Directive
    -0.61
     likely
    -0.61
    GY
    -0.60
     UPS
    -0.60
     Defenders
    -0.59
     Likely
    -0.59
     Communists
    -0.58
     repression
    -0.58
     CONC
    -0.58
    POSITIVE LOGITS
    icol
    1.53
    ilingual
    1.51
    imedia
    1.47
    itudes
    1.41
    ivariate
    1.39
    itud
    1.36
    ipl
    1.35
    iverse
    1.34
    iversal
    1.33
    idis
    1.33
    Activations Density 0.028%

    No Known Activations