© 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. 1-RES-JB
    11. 20127
    Prev
    Next
    INDEX
    Explanations

    references to the concept of creation

    oai_token-act-pair · gpt-3.5-turbo

    references to "creation" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ago
    -0.84
     Statistical
    -0.74
     Caf
    -0.70
     Liqu
    -0.66
    EGA
    -0.65
    mph
    -0.63
     Appl
    -0.61
     Clin
    -0.61
     Analy
    -0.60
     Carb
    -0.60
    POSITIVE LOGITS
     creation
    1.04
    jriwal
    0.95
    smanship
    0.85
    itious
    0.83
    alist
    0.83
    eering
    0.81
    ivism
    0.81
    formation
    0.80
    ivist
    0.79
    reating
    0.78
    Activations Density 0.011%

    No Known Activations