© 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. 7-RES-JB
    11. 23086
    Prev
    Next
    INDEX
    Explanations

    HTML or CSS style attributes within text

    oai_token-act-pair · gpt-3.5-turbo

    references to different styles, particularly regarding aesthetics or design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riel
    -0.75
    azar
    -0.74
    minster
    -0.74
    VEN
    -0.71
     Kira
    -0.67
    inosaur
    -0.67
    ertodd
    -0.66
    sie
    -0.66
    enary
    -0.66
    worth
    -0.66
    POSITIVE LOGITS
    heet
    0.92
    ologies
    0.81
     sheets
    0.75
    styles
    0.74
    edo
    0.72
     sheet
    0.72
    ahead
    0.66
     deviations
    0.65
     deviation
    0.65
    ably
    0.65
    Activations Density 0.030%

    No Known Activations