© 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. 23017
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "warming up" or "preparing" for an activity

    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
    KEY
    -0.72
    ãĥĥãĥī
    -0.70
    APH
    -0.68
    ighthouse
    -0.67
    ushima
    -0.66
    gemony
    -0.63
    SHA
    -0.62
    ighth
    -0.62
    BIT
    -0.61
    HAHAHAHA
    -0.61
    POSITIVE LOGITS
    dates
    1.14
    stairs
    0.90
    rison
    0.87
    dating
    0.83
     affair
    0.77
     scrimmage
    0.72
    rons
    0.71
    oons
    0.68
    alore
    0.68
     tent
    0.68
    Activations Density 0.048%

    No Known Activations