© 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. 7418
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent actions or incidents

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" related to incidents or events

    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
     incumb
    -0.80
     entrants
    -0.70
     endors
    -0.69
    issance
    -0.68
    username
    -0.67
     learners
    -0.65
    wagon
    -0.65
     evolves
    -0.64
     debuted
    -0.63
     announ
    -0.63
    POSITIVE LOGITS
     lieu
    1.20
     conjunction
    1.14
     accordance
    1.08
    humane
    1.05
    ching
    1.02
    jured
    1.00
     situ
    0.99
     tandem
    0.94
     spite
    0.93
     unison
    0.93
    Activations Density 0.316%

    No Known Activations