© 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. 7-RES-JB
    11. 20551
    Prev
    Next
    INDEX
    Explanations

    instances where the word "Obsidian" is mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Obs" or variations of it, indicating a focus on observational data or references

    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
     Melt
    -0.70
    boarding
    -0.69
    Fra
    -0.68
    buster
    -0.67
    channelAvailability
    -0.65
    WAY
    -0.63
    WAYS
    -0.63
     Catalyst
    -0.62
     Horowitz
    -0.62
    warming
    -0.60
    POSITIVE LOGITS
    olesc
    1.34
    olescent
    1.33
    idian
    1.30
    ensible
    1.27
    essional
    1.26
    essed
    1.19
    erver
    1.15
    erving
    1.12
    essions
    1.12
    ervation
    1.11
    Activations Density 0.034%

    No Known Activations