© 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. 1-RES-JB
    11. 24270
    Prev
    Next
    INDEX
    Explanations

    references to events related to inaugurations

    oai_token-act-pair · gpt-3.5-turbo

    references to presidential inaugurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abol
    -0.70
    nda
    -0.70
    lust
    -0.67
    Tier
    -0.65
    thia
    -0.64
    alcohol
    -0.64
    eq
    -0.64
    ied
    -0.63
    thirst
    -0.63
    Gene
    -0.63
    POSITIVE LOGITS
    urated
    1.36
     inauguration
    1.20
    urations
    1.11
    uration
    1.05
     inaug
    1.03
    éĹĺ
    0.93
     Seym
    0.86
    nesday
    0.85
     ceremonies
    0.82
    eering
    0.80
    Activations Density 0.006%

    No Known Activations