© 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. 2768
    Prev
    Next
    INDEX
    Explanations

    information related to averages, medians, wages, prices, and financial data

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data related to income and wages

    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
    eland
    -0.81
    amia
    -0.70
    mbuds
    -0.67
    ternity
    -0.66
     reinforcements
    -0.64
    ascript
    -0.64
    ĪĴ
    -0.64
    itars
    -0.64
    mone
    -0.63
    reditary
    -0.63
    POSITIVE LOGITS
     deviation
    0.88
     (.
    0.74
     lasts
    0.73
     varies
    0.69
     respondent
    0.69
    Length
    0.66
    VALUE
    0.65
     median
    0.64
     gross
    0.64
     percentile
    0.64
    Activations Density 0.180%

    No Known Activations