© 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. 9906
    Prev
    Next
    INDEX
    Explanations

    information related to time, numbers, and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to time and measurements

    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
    chance
    -0.68
    cients
    -0.66
    odox
    -0.64
    inger
    -0.62
     Mate
    -0.61
    bye
    -0.60
    ĪĴ
    -0.60
     Myr
    -0.58
    cest
    -0.58
     brightly
    -0.58
    POSITIVE LOGITS
    VALUE
    0.76
    ngth
    0.75
     liabilities
    0.74
    urden
    0.72
    minus
    0.71
     totals
    0.69
     expenditures
    0.67
     Expend
    0.67
    isations
    0.66
     comprises
    0.66
    Activations Density 0.195%

    No Known Activations