© 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. 20481
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Mis" with a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Mis" or related words, likely referring to a specific entity or concept

    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
     exerc
    -0.76
     Guardians
    -0.68
     Gladiator
    -0.68
     Dull
    -0.66
     Schwarzenegger
    -0.65
     Ragnarok
    -0.64
    è¯
    -0.64
     Defenders
    -0.62
     Irving
    -0.62
     directors
    -0.62
    POSITIVE LOGITS
    ogyn
    1.25
    cellaneous
    1.18
    chief
    1.13
    fortune
    1.12
    guided
    1.00
    leading
    0.98
    placed
    0.96
    beh
    0.94
    aka
    0.93
    represent
    0.91
    Activations Density 0.026%

    No Known Activations