© 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. 10-RES-JB
    11. 21719
    Prev
    Next
    INDEX
    Explanations

    phrases related to principles, beliefs, and foundations

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to foundational principles and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acs
    -0.77
    blow
    -0.74
    apers
    -0.74
    osponsors
    -0.74
    apes
    -0.73
    guards
    -0.72
    dor
    -0.72
    kees
    -0.70
    rection
    -0.69
    apore
    -0.69
    POSITIVE LOGITS
     premise
    1.57
     assumption
    1.46
     belief
    1.41
     principles
    1.29
     principle
    1.29
     misunderstanding
    1.24
     assumptions
    1.18
     misconception
    1.16
     bedrock
    1.15
     notion
    1.13
    Activations Density 0.278%

    No Known Activations