© 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. 20919
    Prev
    Next
    INDEX
    Explanations

    names or parts of names related to the city of "Bor" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Bor" and its variations, indicating a focus on a specific entity or location

    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
    ONSORED
    -0.91
    ITNESS
    -0.83
    encers
    -0.73
     srfAttach
    -0.71
    ULT
    -0.71
     VIDEOS
    -0.71
    UAL
    -0.69
    ELL
    -0.67
    perture
    -0.67
    IDENT
    -0.67
    POSITIVE LOGITS
    ussia
    1.01
    rome
    0.97
    chard
    0.95
    mingham
    0.90
    wana
    0.90
    je
    0.89
    ham
    0.87
    rien
    0.85
    bon
    0.84
    vik
    0.83
    Activations Density 0.012%

    No Known Activations