© 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. 4440
    Prev
    Next
    INDEX
    Explanations

    phrases that end with punctuation marks like quotation marks and periods, with a preference for emphasis markers

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases expressing uncertainty or potential outcomes

    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
     endeav
    -0.81
    aband
    -0.73
    heit
    -0.72
    stab
    -0.66
     censor
    -0.65
     Reincarnated
    -0.65
     centrally
    -0.63
    inyl
    -0.62
     footing
    -0.62
    ittle
    -0.62
    POSITIVE LOGITS
    Newsletter
    1.14
    Contribut
    1.00
    SPONSORED
    0.99
    ONSORED
    0.97
    Asked
    0.96
    Shape
    0.94
    Indeed
    0.94
    Refer
    0.91
    RELATED
    0.90
    Said
    0.86
    Activations Density 0.219%

    No Known Activations