© 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. 8554
    Prev
    Next
    INDEX
    Explanations

    dates or durations mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    chronological markers and references to significant events

    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
    ¬¼
    -0.80
    Ĥª
    -0.73
    eret
    -0.70
     backwards
    -0.68
     upside
    -0.67
     alright
    -0.65
    initely
    -0.65
    ħĭ
    -0.65
     somew
    -0.64
    unity
    -0.64
    POSITIVE LOGITS
     landfall
    0.85
     inception
    0.80
     arrival
    0.80
     onset
    0.80
    ukemia
    0.79
     Titanic
    0.72
    pleted
    0.72
     inauguration
    0.71
     alleged
    0.70
     began
    0.70
    Activations Density 0.309%

    No Known Activations