© 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. 2-RES-JB
    11. 9340
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Don" in relation to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LCS
    -0.75
     Dise
    -0.70
     Healing
    -0.67
     Demand
    -0.66
     Mayhem
    -0.65
     Nightmare
    -0.65
     TIT
    -0.65
    âĹ¼
    -0.64
     Hour
    -0.64
     Built
    -0.64
    POSITIVE LOGITS
    nell
    1.06
    't
    1.05
    ned
    1.02
    nie
    1.00
    ates
    0.99
    ners
    0.98
    ning
    0.95
    etsk
    0.94
    ctory
    0.93
    ating
    0.93
    Activations Density 0.008%

    No Known Activations