© 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. 14261
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to notable individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly with the surname 'Schwe' or 'Sach'

    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
     GEAR
    -0.77
     bipolar
    -0.74
     vic
    -0.73
    姫
    -0.72
    ENTS
    -0.70
    lighting
    -0.67
    LESS
    -0.67
     circumstance
    -0.65
    displayText
    -0.65
     needless
    -0.64
    POSITIVE LOGITS
     Schwe
    1.24
    itzer
    1.12
    acher
    0.94
    issance
    0.93
    etz
    0.90
    ijn
    0.86
    iago
    0.85
     Gaal
    0.84
    geist
    0.82
    isen
    0.82
    Activations Density 0.006%

    No Known Activations