© 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. 7-RES-JB
    11. 11344
    Prev
    Next
    INDEX
    Explanations

    phrases indicating different options or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce alternatives or uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iper
    -0.67
    aturday
    -0.65
    onde
    -0.65
    vertising
    -0.62
    holder
    -0.61
     Reaper
    -0.60
     Donation
    -0.60
    ur
    -0.59
    Ãį
    -0.59
    UR
    -0.59
    POSITIVE LOGITS
     else
    1.05
     alternatively
    1.04
    nam
    1.02
    acles
    0.96
     otherwise
    0.94
    acular
    0.91
    Else
    0.91
    acle
    0.90
    chard
    0.89
    phans
    0.88
    Activations Density 0.119%

    No Known Activations