© 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. 8-RES-JB
    11. 20337
    Prev
    Next
    INDEX
    Explanations

    phrases related to virtual reality environments

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Eve."

    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
    enegger
    -0.74
    assetsadobe
    -0.72
    chrom
    -0.71
    pmwiki
    -0.71
    XM
    -0.68
    iferation
    -0.67
    acca
    -0.66
    ocard
    -0.66
    oho
    -0.66
    artney
    -0.63
    POSITIVE LOGITS
    lyn
    1.14
    rette
    1.04
     Valkyrie
    1.00
    ilon
    0.91
    lla
    0.87
    theless
    0.84
     Eve
    0.81
    lynn
    0.81
    lling
    0.76
    llers
    0.76
    Activations Density 0.065%

    No Known Activations