© 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. 10-RES-JB
    6. 10026
    Prev
    Next
    INDEX
    Explanations

    mentions of official speeches and events, particularly the State of the Union address

    oai_token-act-pair · gpt-3.5-turbo

    references to the State of the Union address and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zon
    -0.74
    finder
    -0.74
    oslav
    -0.71
    alties
    -0.69
    atem
    -0.69
    protein
    -0.67
     cooper
    -0.66
     Agric
    -0.65
    abase
    -0.65
    depend
    -0.64
    POSITIVE LOGITS
     speeches
    1.40
     ceremony
    1.31
     speech
    1.27
     ceremonies
    1.25
     Speech
    1.24
     festivities
    1.16
     podium
    1.11
     celebration
    1.10
     keynote
    1.06
    speech
    1.05
    Activations Density 0.186%

    No Known Activations