© 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. 8-RES-JB
    11. 17756
    Prev
    Next
    INDEX
    Explanations

    phrases expressing comparison and importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negative consequences or concerns regarding youth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DNA
    -0.63
    iste
    -0.61
    SHIP
    -0.61
    dinand
    -0.60
    ngth
    -0.59
    undy
    -0.58
    release
    -0.56
    eln
    -0.56
    "],
    -0.56
    acement
    -0.56
    POSITIVE LOGITS
     importantly
    1.05
     interestingly
    0.84
     guessed
    0.79
     furthermore
    0.79
    Ħ¢
    0.75
     aside
    0.75
     incidentally
    0.73
    versely
    0.72
     moreover
    0.70
     meantime
    0.70
    Activations Density 0.837%

    No Known Activations