© 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. 6-RES-JB
    11. 9828
    Prev
    Next
    INDEX
    Explanations

    numerical values and associated symbols

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with dates and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ications
    -0.84
    ition
    -0.73
    iated
    -0.72
    itions
    -0.72
    elight
    -0.71
    ioned
    -0.70
    icating
    -0.69
    Stage
    -0.68
    uyomi
    -0.68
    istical
    -0.68
    POSITIVE LOGITS
    09
    1.03
    07
    0.97
    08
    0.96
    059
    0.96
    06
    0.96
    05
    0.94
    090
    0.92
    04
    0.91
    089
    0.90
    03
    0.89
    Activations Density 0.077%

    No Known Activations