© 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. 11-RES-JB
    11. 22358
    Prev
    Next
    INDEX
    Explanations

    instances of the word "information"

    oai_token-act-pair · gpt-3.5-turbo

    references to information and its qualities

    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
    aughs
    -0.67
    KR
    -0.67
     Parables
    -0.66
    interstitial
    -0.64
    atos
    -0.64
    kus
    -0.64
    adj
    -0.62
    igham
    -0.61
    luaj
    -0.61
    pex
    -0.61
    POSITIVE LOGITS
     overload
    1.12
     glean
    1.03
     retrieval
    0.96
     theoret
    0.94
     gathered
    0.92
     dissemination
    0.92
     about
    0.89
     gathering
    0.89
     regarding
    0.86
     pertaining
    0.86
    Activations Density 0.053%

    No Known Activations