© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 5008
    Prev
    Next
    INDEX
    Explanations

    references to vengeance and justice

    oai_token-act-pair · gpt-3.5-turbo

    references to themes of vengeance and retribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umably
    -0.75
    entially
    -0.74
    related
    -0.71
    ONSORED
    -0.67
    photo
    -0.67
    RM
    -0.67
     Activities
    -0.65
    Basically
    -0.65
    obby
    -0.63
    ixel
    -0.63
    POSITIVE LOGITS
     darkness
    1.19
     sorrow
    1.17
     everlasting
    1.15
     souls
    1.14
     eternal
    1.13
     sinners
    1.13
     mercy
    1.08
     gods
    1.07
     ashes
    1.07
     righteousness
    1.06
    Activations Density 1.012%

    No Known Activations