© 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. 6-RES-JB
    11. 9878
    Prev
    Next
    INDEX
    Explanations

    the word "power" at varying degrees of relevance or strength

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of power in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Von
    -0.77
    ALK
    -0.76
     Admission
    -0.71
    romeda
    -0.70
    eret
    -0.69
    verett
    -0.68
     Taste
    -0.67
    ç«
    -0.67
    eryl
    -0.67
    eday
    -0.66
    POSITIVE LOGITS
    houses
    0.99
    stroke
    0.94
    FUL
    0.92
    lessness
    0.91
     vested
    0.90
     levers
    0.89
     outage
    0.85
     wielded
    0.84
    puff
    0.81
     imbalance
    0.80
    Activations Density 0.039%

    No Known Activations