© 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. 4-RES-JB
    11. 22093
    Prev
    Next
    INDEX
    Explanations

    references to a location named "Rocky Top" or terms related to cowboys and cowboy culture

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Rocky" or "Rocky Mountain" entities and related terms

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

    No Comments

    Negative Logits
    */(
    -0.90
    lessly
    -0.83
    usc
    -0.80
    ogl
    -0.79
    mble
    -0.78
    ozyg
    -0.76
    inia
    -0.75
    istics
    -0.75
    ugu
    -0.75
    iners
    -0.74
    POSITIVE LOGITS
     Mountain
    0.87
     Helmet
    0.83
     Mountains
    0.80
     Rocky
    0.78
     Horror
    0.76
     Romero
    0.75
     Dreams
    0.74
     Bal
    0.74
     River
    0.73
    cliffe
    0.72
    Activations Density 0.015%

    No Known Activations