© 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. 11-RES-JB
    11. 18747
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specific locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations or occurrences within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HAEL
    -0.72
    :/
    -0.70
    lot
    -0.70
    dule
    -0.69
    ById
    -0.66
    roximately
    -0.64
    0000000000000000
    -0.64
    iris
    -0.64
    enza
    -0.63
    romeda
    -0.62
    POSITIVE LOGITS
     academia
    1.36
     circles
    1.07
     Silicon
    0.98
     favor
    0.94
     Congress
    0.94
     Europe
    0.91
     favour
    0.91
     academ
    0.90
     Washington
    0.90
     fandom
    0.87
    Activations Density 0.172%

    No Known Activations