© 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. 4430
    Prev
    Next
    INDEX
    Explanations

    entities related to government and political figures, particularly in the context of decisions or controversies

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms indicating ownership or association

    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
    raviolet
    -0.69
     gist
    -0.65
    awaru
    -0.65
    ebus
    -0.61
     rhy
    -0.61
     KC
    -0.60
    odium
    -0.60
     pressures
    -0.60
     carbohyd
    -0.60
    merce
    -0.60
    POSITIVE LOGITS
    女
    1.00
    ï¸ı
    0.89
    Ļ
    0.88
    ãĥ¥
    0.86
    éĩ
    0.83
    ¯¯
    0.83
    ħ
    0.81
    SHIP
    0.80
    Ùħ
    0.80
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.80
    Activations Density 0.526%

    No Known Activations