© 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. 13112
    Prev
    Next
    INDEX
    Explanations

    references to fictional or mythical elements, such as artifacts, legends, and lore

    oai_token-act-pair · gpt-3.5-turbo

    references to "lore" and its related concepts

    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
    ressive
    -0.71
    ertility
    -0.71
    otonin
    -0.64
    deen
    -0.63
    ennett
    -0.63
    Monitor
    -0.63
     Loans
    -0.63
    Arab
    -0.62
    ablishment
    -0.60
    edience
    -0.60
    POSITIVE LOGITS
     lore
    1.10
    lore
    0.95
     trivia
    0.85
    nz
    0.80
    abilia
    0.78
     tale
    0.75
     tales
    0.73
    theless
    0.71
     relics
    0.69
    telling
    0.68
    Activations Density 0.013%

    No Known Activations