© 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. 3238
    Prev
    Next
    INDEX
    Explanations

    phrases indicating representation or significance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate representation or significance

    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
    jar
    -0.64
    intend
    -0.61
    ita
    -0.61
    roit
    -0.60
    imb
    -0.60
    ibel
    -0.60
    erm
    -0.60
    erman
    -0.60
     behaved
    -0.60
    ithing
    -0.60
    POSITIVE LOGITS
    Interstitial
    0.83
     an
    0.77
     a
    0.73
     something
    0.70
    orically
    0.68
    reement
    0.67
    Operation
    0.66
     sacrifices
    0.66
     salvation
    0.66
    agi
    0.66
    Activations Density 0.072%

    No Known Activations