© 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. 22253
    Prev
    Next
    INDEX
    Explanations

    phrases related to being capable or skilled in various subjects or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to personal abilities and qualities, particularly those associated with being "good" or "well-looking."

    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
     guiActiveUn
    -0.87
    çīĪ
    -0.84
    ĸļ
    -0.80
    pora
    -0.71
    £ı
    -0.67
    JM
    -0.66
    otom
    -0.65
    amera
    -0.63
    irez
    -0.63
    ural
    -0.62
    POSITIVE LOGITS
    itives
    0.68
    ailability
    0.64
    âĹ¼
    0.61
    hearted
    0.61
     Okawaru
    0.61
    tein
    0.60
    hum
    0.60
     fodder
    0.60
     Hunting
    0.60
     Hide
    0.59
    Activations Density 0.253%

    No Known Activations