© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 160
    Prev
    Next
    INDEX
    Explanations

    terms related to authority or importance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to authority or superiority, particularly in legal or governing contexts

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

    No Comments

    Negative Logits
    OUT
    -0.88
    ppo
    -0.84
    TPS
    -0.72
    zl
    -0.72
    ople
    -0.71
    okemon
    -0.67
    agic
    -0.67
    д
    -0.67
    EEK
    -0.66
    FORE
    -0.66
    POSITIVE LOGITS
    ly
    0.86
    rament
    0.82
     ruler
    0.76
    iour
    0.74
     referen
    0.73
    most
    0.72
     decree
    0.71
     punishment
    0.70
     administrator
    0.70
    reme
    0.69
    Activations Density 0.013%

    No Known Activations