© 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. 1449
    Prev
    Next
    INDEX
    Explanations

    politician names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific political figures, particularly "Sarkozy" and "Sardari."

    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
    âĸ¬âĸ¬
    -0.67
    oration
    -0.67
    Universal
    -0.63
     Independence
    -0.63
    orate
    -0.62
    LEASE
    -0.62
    20439
    -0.62
     Greenwich
    -0.61
     needless
    -0.61
    66666666
    -0.61
    POSITIVE LOGITS
    ozy
    1.43
     Sark
    1.02
    indal
    1.00
    daq
    0.93
    olini
    0.89
    esian
    0.85
    ano
    0.85
    inia
    0.84
    ansas
    0.82
    nown
    0.81
    Activations Density 0.006%

    No Known Activations