© 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. 17366
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to an organization named "Heritage Foundation."

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a specific entity, namely the Heritage Foundation

    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
     unsub
    -0.71
    ysis
    -0.67
    eln
    -0.66
    taboola
    -0.66
    sis
    -0.66
    romeda
    -0.66
    umi
    -0.62
    erm
    -0.62
    rieg
    -0.61
    tered
    -0.61
    POSITIVE LOGITS
    conservancy
    1.00
     Heritage
    0.98
    itage
    0.84
    icity
    0.82
     Foundation
    0.79
     Commons
    0.77
     Preservation
    0.77
    fulness
    0.76
     Collection
    0.75
     Institutes
    0.74
    Activations Density 0.027%

    No Known Activations