© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20282
    Prev
    Next
    INDEX
    Explanations

    company or personal names containing the word "ner"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ner" across various contexts

    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
    DonaldTrump
    -0.70
    ERA
    -0.64
    erity
    -0.63
    carry
    -0.60
     Rouhani
    -0.60
    avorite
    -0.59
    ptives
    -0.59
     unrealistic
    -0.55
     VIDE
    -0.55
    ĸļ
    -0.54
    POSITIVE LOGITS
    stocks
    1.06
    getic
    1.01
    gie
    1.00
    stein
    0.99
    nen
    0.97
    lund
    0.95
    ning
    0.95
    sonian
    0.94
    dal
    0.94
    ding
    0.93
    Activations Density 0.060%

    No Known Activations