© 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. 0-RES-JB
    11. 14004
    Prev
    Next
    INDEX
    Explanations

    names related to politics and government figures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring 'ir'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scrolls
    -0.65
     Kendall
    -0.63
     classification
    -0.62
     lif
    -0.61
     thrown
    -0.61
     Etsy
    -0.59
     Quality
    -0.58
     âĪ
    -0.57
     appl
    -0.57
     posted
    -0.56
    POSITIVE LOGITS
    ir
    4.19
    irs
    2.93
    IR
    2.00
    ira
    1.91
    irin
    1.89
    iri
    1.83
    iral
    1.83
    iris
    1.78
    rir
    1.65
    ire
    1.64
    Activations Density 0.027%

    No Known Activations