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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14798
    Prev
    Next
    INDEX
    Explanations

    references to the city of Bogota

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Bog" in various contexts

    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
    ensional
    -0.73
    aeda
    -0.65
    IELD
    -0.64
    ilial
    -0.62
    natureconservancy
    -0.60
    ULTS
    -0.60
    idency
    -0.60
     infertility
    -0.59
    Running
    -0.59
     FANTASY
    -0.59
    POSITIVE LOGITS
    asus
    1.02
    ging
    0.99
    ovy
    0.97
    oslav
    0.97
     Bog
    0.96
    ged
    0.91
    oken
    0.89
    ota
    0.88
    owitz
    0.88
    glers
    0.86
    Activations Density 0.006%

    No Known Activations