© 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. 8888
    Prev
    Next
    INDEX
    Explanations

    approval-related terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to approvals 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
    hed
    -0.86
    gm
    -0.78
    kt
    -0.77
    ãĤ©
    -0.76
     Hebdo
    -0.75
    grave
    -0.72
    lla
    -0.71
    tein
    -0.71
    Corn
    -0.68
    tal
    -0.68
    POSITIVE LOGITS
     approval
    1.49
     approvals
    1.42
     approves
    1.10
     approving
    1.02
     ratings
    1.02
     rating
    0.98
     approve
    0.97
     Appro
    0.96
    appro
    0.96
     ratification
    0.96
    Activations Density 0.012%

    No Known Activations