© 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. 6762
    Prev
    Next
    INDEX
    Explanations

    references to the celestial body or moon named "Europa"

    oai_token-act-pair · gpt-3.5-turbo

    references to the moon Europa

    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
    enegger
    -1.19
    allow
    -0.81
    yang
    -0.80
    nu
    -0.78
    smith
    -0.78
    ym
    -0.77
    ships
    -0.75
    intosh
    -0.74
    saw
    -0.72
    orses
    -0.72
    POSITIVE LOGITS
     Europa
    1.01
     strugg
    0.71
     Knot
    0.71
     differe
    0.67
     League
    0.66
     coefficient
    0.66
    ©¶æ¥µ
    0.66
     goalkeeper
    0.66
     slump
    0.65
    lehem
    0.64
    Activations Density 0.006%

    No Known Activations