© 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. 18410
    Prev
    Next
    INDEX
    Explanations

    key phrases with repetitive mentions of the word "fact" and emphasizing on the stated information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to established or important facts

    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
    avorite
    -0.96
     livest
    -0.72
     awa
    -0.69
    asca
    -0.67
    itsch
    -0.66
    airs
    -0.66
    artney
    -0.66
    ESE
    -0.66
     Skies
    -0.63
     lungs
    -0.63
    POSITIVE LOGITS
    ually
    1.11
    ional
    1.09
    orial
    1.04
    uality
    1.03
    itious
    0.88
    oids
    0.86
    uate
    0.84
    uation
    0.79
    finding
    0.78
    uel
    0.77
    Activations Density 0.020%

    No Known Activations