© 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. 9764
    Prev
    Next
    INDEX
    Explanations

    references to the comic book series X-Men

    oai_token-act-pair · gpt-3.5-turbo

    references to the "X-Men" franchise

    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
    kson
    -0.88
    assetsadobe
    -0.79
    sburgh
    -0.75
     Lauder
    -0.75
    м
    -0.72
    kamp
    -0.71
    Ú
    -0.70
    ATURES
    -0.69
    getic
    -0.69
     captcha
    -0.68
    POSITIVE LOGITS
    posed
    1.12
    avier
    1.05
    yz
    0.99
    peria
    0.96
    XXXX
    0.96
    IX
    0.91
    odus
    0.87
    iao
    0.87
     chromosome
    0.84
     chromosomes
    0.81
    Activations Density 0.027%

    No Known Activations