© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 6351
    Prev
    Next
    INDEX
    Explanations

    text enclosed in square brackets with the acronym "sic" denoting a mistake

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to references or citations, particularly in the context of scientific or formal discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sund
    -0.70
    ĪĴ
    -0.70
    EVA
    -0.67
    è»
    -0.64
    VIEW
    -0.63
    MQ
    -0.63
    OHN
    -0.62
    knit
    -0.61
    fman
    -0.60
    Arm
    -0.60
    POSITIVE LOGITS
    rano
    0.89
    terday
    0.88
    aminer
    0.86
    !]
    0.85
    .,
    0.84
    ]
    0.81
    istical
    0.79
    ername
    0.78
    uality
    0.77
    ]'
    0.76
    Activations Density 0.026%

    No Known Activations