© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 15006
    Prev
    Next
    INDEX
    Explanations

    phrases related to books and reading

    oai_token-act-pair · gpt-3.5-turbo

    references to books and related media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ral
    -0.74
    ²¾
    -0.68
    dds
    -0.66
    orld
    -0.66
    ajor
    -0.63
    ilities
    -0.62
    ords
    -0.62
     Males
    -0.61
     Methods
    -0.61
    ollah
    -0.60
    POSITIVE LOGITS
    maker
    0.91
    wright
    0.88
    buy
    0.82
    seller
    0.79
    makers
    0.78
    stores
    0.75
    making
    0.74
     titles
    0.73
     genres
    0.72
    genre
    0.71
    Activations Density 0.337%

    No Known Activations