© 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. 0-RES-JB
    11. 15531
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Eddie"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Eddie."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cro
    -0.79
     Rus
    -0.70
    Susan
    -0.69
     cp
    -0.67
     SHAR
    -0.67
     Sri
    -0.67
     backbone
    -0.66
    Wr
    -0.66
     ribbon
    -0.65
    natureconservancy
    -0.65
    POSITIVE LOGITS
     Oilers
    1.68
     Eddie
    1.66
     Edmonton
    1.62
     Eld
    1.60
    ollah
    1.40
     OLED
    1.16
     Tav
    1.15
     Eminem
    1.06
    monton
    1.06
     Ez
    1.05
    Activations Density 0.040%

    No Known Activations