Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 2272
    Prev
    Next
    INDEX
    Explanations

    special characters often used in non-English languages

    oai_token-act-pair · gpt-3.5-turbo

    special characters or unusual symbols

    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
    Downloadha
    -0.85
    cius
    -0.73
    racuse
    -0.72
    zona
    -0.71
    ourke
    -0.70
     Danger
    -0.67
    angers
    -0.67
    rament
    -0.67
    lycer
    -0.66
    raints
    -0.66
    POSITIVE LOGITS
    ¼
    1.14
    ł
    1.03
    ³
    1.02
    Ķ
    1.01
    ¹
    0.98
    ħ
    0.97
    »
    0.95
    ·
    0.95
    ¸
    0.91
    º
    0.91
    Activations Density 0.004%

    No Known Activations