© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1448
    Prev
    Next
    INDEX
    Explanations

    mentions of the phrase "Heritage Foundation."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Heritage Foundation

    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
     uncond
    -0.72
    dj
    -0.70
     volts
    -0.67
     coer
    -0.66
     paralysis
    -0.65
    vr
    -0.65
     rat
    -0.65
     rats
    -0.64
     confined
    -0.63
     bugs
    -0.63
    POSITIVE LOGITS
     Heritage
    4.06
    itage
    1.96
     heritage
    1.70
     Historic
    1.34
     Antiqu
    1.18
     Preservation
    1.10
     Legacy
    1.05
     Cultural
    1.04
     Historical
    1.01
     Century
    1.01
    Activations Density 0.016%

    No Known Activations