© 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. 17105
    Prev
    Next
    INDEX
    Explanations

    mentions of the author Aldous Huxley's name

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Huxley."

    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
    à¨
    -0.76
    ALLY
    -0.73
     à¨
    -0.73
    à¤
    -0.71
    ¶ħ
    -0.69
    ANK
    -0.68
    ¢
    -0.68
     Croat
    -0.68
    à©
    -0.66
    BILL
    -0.66
    POSITIVE LOGITS
    iliary
    1.27
    edo
    1.18
    uries
    1.13
    urious
    1.13
    ury
    1.08
    uria
    1.07
    xes
    1.03
    avier
    1.00
    eus
    0.96
    es
    0.92
    Activations Density 0.008%

    No Known Activations