© 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. 21982
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the letter character "Ļ"

    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
     Seym
    -0.57
     mathemat
    -0.56
     vulner
    -0.54
     carbohyd
    -0.52
     exha
    -0.51
     hemor
    -0.49
     princ
    -0.48
     pleasures
    -0.48
     contrace
    -0.47
     misunder
    -0.47
    POSITIVE LOGITS
    ï¸ı
    0.89
    gypt
    0.63
    ï¸
    0.61
    KK
    0.61
    VICE
    0.59
    Balt
    0.59
    ··
    0.57
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.57
    ¯
    0.57
    Lind
    0.56
    Activations Density 0.594%

    No Known Activations