© 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. 6-RES-JB
    11. 15226
    Prev
    Next
    INDEX
    Explanations

    mentions of numerical totals or amounts in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "total" in various contexts, particularly in relation to sums or quantities

    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
    assies
    -0.79
    ells
    -0.77
     buttons
    -0.72
     lobb
    -0.71
    ulations
    -0.70
     newsletters
    -0.67
    esters
    -0.66
    tics
    -0.64
     Keys
    -0.63
     Scouts
    -0.63
    POSITIVE LOGITS
    ©¶æ¥µ
    0.89
    è¦ļéĨĴ
    0.79
    ccording
    0.75
    ãĥ¼ãĥĨãĤ£
    0.71
     number
    0.70
     760
    0.69
     amount
    0.68
     costing
    0.67
     standpoint
    0.67
     estimate
    0.66
    Activations Density 0.130%

    No Known Activations