© 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. 9-RES-JB
    11. 14091
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic indicators, poverty levels, and fiscal policies

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to poverty and economic thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.77
    >>>>>>>>
    -0.67
    "]=>
    -0.66
    kef
    -0.65
    multiple
    -0.65
    among
    -0.63
    raq
    -0.63
    especially
    -0.60
     notwithstanding
    -0.60
     symbolism
    -0.60
    POSITIVE LOGITS
     originals
    1.12
     baseline
    1.03
     usual
    0.99
     nearest
    0.99
     average
    0.96
     normal
    0.94
     previous
    0.93
    normal
    0.91
     norm
    0.91
     original
    0.89
    Activations Density 0.449%

    No Known Activations