© 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. 10726
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statements or quoting someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "says" or "said" and its variations, indicating statements or quotations

    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
    estern
    -0.88
    folios
    -0.76
    theless
    -0.70
    anu
    -0.70
    thia
    -0.68
    aughs
    -0.68
    udos
    -0.67
    MENTS
    -0.65
    Tai
    -0.64
    posium
    -0.63
    POSITIVE LOGITS
     goodbye
    1.02
     nothing
    0.69
    ysis
    0.66
    ogun
    0.63
     otherwise
    0.63
     yes
    0.62
    ieu
    0.61
     bye
    0.60
     spies
    0.59
    auga
    0.59
    Activations Density 0.131%

    No Known Activations