© 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. 19347
    Prev
    Next
    INDEX
    Explanations

    words related to news articles and events

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events impacting public safety or health

    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
    ãĤ¦ãĤ¹
    -0.68
    colour
    -0.67
    Firstly
    -0.66
     tremend
    -0.64
     Whilst
    -0.64
     dstg
    -0.62
    à¨
    -0.62
    reetings
    -0.60
    ãĥij
    -0.60
     hegemony
    -0.60
    POSITIVE LOGITS
     meanwhile
    0.92
     declined
    0.86
     afterward
    0.86
     also
    0.85
     later
    0.82
     unsuccessfully
    0.81
     however
    0.79
     totaled
    0.79
     additionally
    0.78
     therefore
    0.78
    Activations Density 1.360%

    No Known Activations