© 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. 2065
    Prev
    Next
    INDEX
    Explanations

    references related to hearing impairment

    oai_token-act-pair · gpt-3.5-turbo

    references to deafness and visually impaired conditions

    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
    anu
    -0.70
    ################
    -0.67
    izoph
    -0.65
     Smooth
    -0.64
     Heights
    -0.64
    Pool
    -0.63
    andals
    -0.63
    vier
    -0.62
     constituent
    -0.62
    kr
    -0.61
    POSITIVE LOGITS
    heed
    1.01
    cephal
    0.90
    elines
    0.88
    ening
    0.81
    etr
    0.77
    figured
    0.75
    etry
    0.74
    etrical
    0.74
    iple
    0.74
    emia
    0.73
    Activations Density 0.060%

    No Known Activations