© 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. 8-RES-JB
    11. 7795
    Prev
    Next
    INDEX
    Explanations

    phrases related to people or groups of people and their actions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people and their actions or characteristics

    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
    taboola
    -0.78
     unspecified
    -0.68
    Attempts
    -0.64
    quet
    -0.64
    =\"
    -0.63
    inks
    -0.63
    Increases
    -0.62
    cation
    -0.61
    EMBER
    -0.61
    \\\\\\\\
    -0.61
    POSITIVE LOGITS
     populate
    0.83
     comprise
    0.80
     constitute
    0.70
     inhabit
    0.68
     composing
    0.68
     aren
    0.67
     weren
    0.65
     were
    0.64
     surround
    0.64
     acad
    0.64
    Activations Density 0.465%

    No Known Activations