© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 21832
    Prev
    Next
    INDEX
    Explanations

    the word "record" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rec" in various forms, suggesting a focus on recording or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sting
    -0.74
     Force
    -0.69
     Tasman
    -0.69
     Khe
    -0.68
     force
    -0.66
     Frenchman
    -0.65
     Athena
    -0.64
     stripe
    -0.61
     Hipp
    -0.60
     Pegasus
    -0.60
    POSITIVE LOGITS
    ursive
    1.17
    urrent
    1.10
    ipes
    1.07
    oded
    1.06
    ycle
    1.06
    ipient
    1.03
    ording
    1.01
    ords
    0.99
    ourses
    0.99
    ourse
    0.97
    Activations Density 0.005%

    No Known Activations