© 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. 11-RES-JB
    11. 1764
    Prev
    Next
    INDEX
    Explanations

    phrases related to rankings or positions

    oai_token-act-pair · gpt-3.5-turbo

    references to national attributes or conditions

    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
    anwhile
    -0.77
     interf
    -0.75
     photoc
    -0.72
     NEC
    -0.70
     Mous
    -0.67
     Syd
    -0.67
     encount
    -0.65
     decomp
    -0.65
     transc
    -0.64
     predec
    -0.63
    POSITIVE LOGITS
    Ļ
    1.57
    ¬
    1.41
    ı
    1.37
    ¡
    1.35
    ¤
    1.34
    ª
    1.32
    Ĵ
    1.31
    ĸ
    1.28
    į
    1.26
    ħ
    1.26
    Activations Density 0.278%

    No Known Activations