© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 23353
    Prev
    Next
    INDEX
    Explanations

    names or words related to "Witt"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "itt" and its variations within the text

    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
    cles
    -0.65
     womb
    -0.63
     psychiat
    -0.59
    ©¶æ
    -0.58
     Belg
    -0.57
    Copy
    -0.56
    SOURCE
    -0.56
    CONT
    -0.55
     departure
    -0.54
     veins
    -0.54
    POSITIVE LOGITS
    sburgh
    1.63
    erella
    1.08
    les
    1.07
    orio
    1.07
    leness
    1.00
    lest
    0.99
    oral
    0.94
    erer
    0.94
    erers
    0.91
    omo
    0.88
    Activations Density 0.029%

    No Known Activations