© 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. 3171
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing attention or providing additional information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "more" and phrases indicating additional information or continuation

    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
    ij士
    -0.71
     Peaks
    -0.68
    ãĤ´ãĥ³
    -0.62
     Viper
    -0.62
     bye
    -0.61
     Penguins
    -0.61
     catcher
    -0.61
     Cros
    -0.59
     majority
    -0.58
    taboola
    -0.58
    POSITIVE LOGITS
     than
    0.97
    erous
    0.93
    than
    0.89
    uries
    0.80
    worldly
    0.79
    efficient
    0.77
    culated
    0.75
    minecraft
    0.74
    é¾įå
    0.74
    artments
    0.71
    Activations Density 0.178%

    No Known Activations