© 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. 13894
    Prev
    Next
    INDEX
    Explanations

    the concept of an "idea"

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "idea" in 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
    ificant
    -0.76
    eworthy
    -0.73
    ancers
    -0.73
    eneg
    -0.69
    eded
    -0.68
    ndum
    -0.67
    eding
    -0.64
    ternity
    -0.63
    eder
    -0.63
    gar
    -0.63
    POSITIVE LOGITS
    ually
    1.15
     idea
    1.13
     concept
    0.87
     moot
    0.85
     premise
    0.85
     Idea
    0.81
     Ideas
    0.79
    yout
    0.78
     proposition
    0.77
     ideas
    0.76
    Activations Density 0.018%

    No Known Activations