© 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. 1-RES-JB
    11. 359
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "Hollins" with variations

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Hollins."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PDATE
    -0.69
     schizophrenia
    -0.68
    ribune
    -0.65
     depression
    -0.64
    healthy
    -0.64
     partial
    -0.63
    riminal
    -0.62
    esthetic
    -0.62
    culosis
    -0.62
    aepernick
    -0.62
    POSITIVE LOGITS
    iday
    1.24
     Holl
    1.08
    idays
    1.06
    aday
    0.90
    ipop
    0.89
    inger
    0.89
    ijn
    0.89
    ippi
    0.84
    inson
    0.78
    ieu
    0.77
    Activations Density 0.008%

    No Known Activations