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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 14797
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names associated with places and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     notor
    -0.87
     acknow
    -0.84
     tremend
    -0.79
     seiz
    -0.76
     confir
    -0.75
     borne
    -0.74
     withd
    -0.73
     recourse
    -0.73
    depending
    -0.72
     administ
    -0.71
    POSITIVE LOGITS
     Productions
    1.23
     Studios
    1.13
     Brewing
    1.05
     Farms
    1.00
     Cafe
    0.98
     Syndrome
    0.95
     Records
    0.94
     Collective
    0.93
     Brigade
    0.92
     Labs
    0.92
    Activations Density 0.296%

    No Known Activations