© 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. 14404
    Prev
    Next
    INDEX
    Explanations

    scientific and philosophical terms related to early natural sciences

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to ethics, morality, and philosophical discourse

    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
     backup
    -0.66
    AMI
    -0.59
     renovations
    -0.59
     helicop
    -0.59
     lookout
    -0.58
    ãĥ¼ãĥ³
    -0.56
     rehab
    -0.56
    pload
    -0.55
     backups
    -0.55
     Jagu
    -0.55
    POSITIVE LOGITS
    itarian
    0.75
     Marxism
    0.72
     philosophers
    0.71
     nihil
    0.70
     Hegel
    0.66
     Zionism
    0.65
     religion
    0.64
     Christianity
    0.64
     ideology
    0.63
     Islam
    0.63
    Activations Density 1.416%

    No Known Activations