© 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. 10666
    Prev
    Next
    INDEX
    Explanations

    terms related to providing accommodations or adjustments to meet specific needs or requirements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "accommodate" in various contexts

    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
    cham
    -0.72
     brow
    -0.72
    fu
    -0.67
    chat
    -0.67
    Downloadha
    -0.65
    otine
    -0.64
    call
    -0.63
    ³³³³³³³³³³³³³³³³
    -0.63
    chem
    -0.62
    intel
    -0.60
    POSITIVE LOGITS
     accommodate
    0.91
    ments
    0.88
    Ĥª
    0.83
    ¿½
    0.78
     Pwr
    0.78
     accommodations
    0.77
     accommodation
    0.76
     accommod
    0.76
     SERV
    0.74
    edIn
    0.73
    Activations Density 0.013%

    No Known Activations