© 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. 4341
    Prev
    Next
    INDEX
    Explanations

    the concept of a physical location being situated at an end or edge of something

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "end" 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
    ĨĴ
    -0.79
    PDATE
    -0.74
     Flavoring
    -0.73
    £ı
    -0.67
    veyard
    -0.65
     irregular
    -0.64
    éĹĺ
    -0.63
    issance
    -0.63
    çİĭ
    -0.62
     Conquest
    -0.62
    POSITIVE LOGITS
    angering
    1.12
    owment
    1.01
    angers
    0.89
    ocrin
    0.88
    spin
    0.88
    ocrine
    0.87
    tackle
    0.83
    game
    0.83
    phal
    0.82
    tails
    0.78
    Activations Density 0.034%

    No Known Activations