© 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. 20563
    Prev
    Next
    INDEX
    Explanations

    phrases related to quotes or speech attributions

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol that may indicate a quote or emphasis

    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
     decomp
    -0.75
     scatter
    -0.71
    OTOS
    -0.71
     spiral
    -0.70
     bunk
    -0.70
     cyan
    -0.66
     habit
    -0.65
     minim
    -0.64
     cruising
    -0.64
     glam
    -0.64
    POSITIVE LOGITS
    said
    1.03
    cause
    0.90
    according
    0.89
    then
    0.88
    say
    0.86
    unless
    0.85
    especially
    0.85
    £
    0.80
    yet
    0.79
    º
    0.79
    Activations Density 0.137%

    No Known Activations