© 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. 3-RES-JB
    11. 2386
    Prev
    Next
    INDEX
    Explanations

    specific strings of characters or acronyms that are unique and repeated multiple times

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.65
     plates
    -0.64
    bell
    -0.63
    birds
    -0.63
    pora
    -0.61
    kiss
    -0.61
    xon
    -0.61
    iris
    -0.61
    Constructed
    -0.60
    strength
    -0.59
    POSITIVE LOGITS
    UD
    1.05
    PDATE
    0.95
    nesday
    0.93
    iamond
    0.92
    IFIED
    0.91
    PLIC
    0.91
    elta
    0.87
    BLE
    0.84
    ITY
    0.83
    geon
    0.81
    Activations Density 0.012%

    No Known Activations