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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 15848
    Prev
    Next
    INDEX
    Explanations

    words containing the substring 'ner'

    oai_token-act-pair · gpt-3.5-turbo

    the word "ner" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DonaldTrump
    -0.76
    avorite
    -0.65
    Breaking
    -0.63
    ERA
    -0.63
    reaching
    -0.60
    carry
    -0.59
    bringing
    -0.58
    ĸļ
    -0.58
    raising
    -0.57
    ptives
    -0.57
    POSITIVE LOGITS
    getic
    1.06
    ding
    1.04
    gie
    1.04
    ning
    0.99
    stein
    0.96
    sonian
    0.94
    lund
    0.90
    dal
    0.87
    ned
    0.84
    ds
    0.83
    Activations Density 0.082%

    No Known Activations