© 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. 11-RES-JB
    11. 18788
    Prev
    Next
    INDEX
    Explanations

    lyrics from songs

    oai_token-act-pair · gpt-3.5-turbo

    instances of special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mous
    -0.85
    Þ
    -0.83
     tremend
    -0.82
    anwhile
    -0.82
     princ
    -0.81
     eleph
    -0.81
     scrambling
    -0.77
     ASC
    -0.77
     sacrific
    -0.75
     conduc
    -0.75
    POSITIVE LOGITS
    ľ
    1.72
    ł
    1.25
    Ķ
    1.21
    Ŀ
    1.20
    ļ
    1.12
    Ł
    1.08
    ĺ
    1.07
    IJ
    1.04
    ¤
    1.03
    ¼
    1.02
    Activations Density 0.204%

    No Known Activations