© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20294
    Prev
    Next
    INDEX
    Explanations

    verbs related to exerting pressure or control on someone or something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "force" in various contexts

    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
    mbuds
    -0.86
    nings
    -0.74
    vironment
    -0.72
    rou
    -0.69
    umer
    -0.69
    mal
    -0.68
    ership
    -0.67
    aird
    -0.67
    orkshire
    -0.67
    nam
    -0.67
    POSITIVE LOGITS
     overtime
    0.85
    otom
    0.85
     conversions
    0.78
     compliance
    0.76
     us
    0.75
     confessions
    0.75
     laborers
    0.73
     concessions
    0.72
     entry
    0.72
     newcomers
    0.72
    Activations Density 0.040%

    No Known Activations