© 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. 3-RES-JB
    11. 10621
    Prev
    Next
    INDEX
    Explanations

    names or references to individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the currency Ruble

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EMBER
    -0.78
    æ©Ł
    -0.68
     à¨
    -0.67
    SOURCE
    -0.67
    ulhu
    -0.66
    orthy
    -0.64
    ECTION
    -0.64
     Titanic
    -0.64
     Hiroshima
    -0.63
    OTAL
    -0.63
    POSITIVE LOGITS
    bing
    1.28
    bish
    1.14
    instein
    1.03
    bles
    1.02
    bed
    0.99
    bers
    0.97
    enstein
    0.96
    pees
    0.91
    inson
    0.89
    Rub
    0.88
    Activations Density 0.004%

    No Known Activations