© 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. 9-RES-JB
    11. 15099
    Prev
    Next
    INDEX
    Explanations

    names or words related to the word "Scarlet"

    oai_token-act-pair · gpt-3.5-turbo

    words relating to specific names or identifiers, particularly with the suffix 'ia' and variations of 'ie'

    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
     oath
    -0.66
     ABE
    -0.61
     Believe
    -0.61
     Masquerade
    -0.58
     lodge
    -0.58
     Scand
    -0.57
     Oath
    -0.56
     bru
    -0.56
     Accord
    -0.55
     COUR
    -0.55
    POSITIVE LOGITS
    omi
    0.98
    bert
    0.93
    ī
    0.88
    xus
    0.84
    vi
    0.83
    xit
    0.83
    º
    0.82
    yi
    0.81
    ¾
    0.79
    lon
    0.77
    Activations Density 0.137%

    No Known Activations