© 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. 8-RES-JB
    11. 18531
    Prev
    Next
    INDEX
    Explanations

    phrases related to philosophy and the pursuit of truth

    oai_token-act-pair · gpt-3.5-turbo

    concepts and discussions related to philosophy and ideology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Alert
    -0.75
    bats
    -0.75
    osponsors
    -0.72
    CDC
    -0.70
    Rail
    -0.68
    RF
    -0.68
     nationwide
    -0.68
    Senator
    -0.67
     ransomware
    -0.66
    CBS
    -0.66
    POSITIVE LOGITS
     oneself
    1.10
     abstraction
    0.94
     spont
    0.94
     perfection
    0.94
     emptiness
    0.92
     imperfect
    0.91
     oppos
    0.89
     rationality
    0.88
     abstract
    0.88
     righteousness
    0.87
    Activations Density 1.415%

    No Known Activations