© 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. 10-RES-JB
    11. 21340
    Prev
    Next
    INDEX
    Explanations

    food companies and businesses related to development and construction

    oai_token-act-pair · gpt-3.5-turbo

    names of companies or organizations

    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
    liest
    -0.87
    istically
    -0.80
     tide
    -0.71
    rette
    -0.70
    less
    -0.68
    adic
    -0.67
    lier
    -0.67
    otos
    -0.66
    aneously
    -0.66
    obin
    -0.65
    POSITIVE LOGITS
    '
    1.64
    hips
    1.52
    ystem
    1.45
    mith
    1.44
    hip
    1.41
    pace
    1.36
    peed
    1.34
    chool
    1.30
    kaya
    1.23
    pring
    1.23
    Activations Density 0.267%

    No Known Activations