© 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. 3-RES-JB
    11. 15231
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements or decisions being made

    oai_token-act-pair · gpt-3.5-turbo

    agreements and consensus in discussions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.78
     glands
    -0.76
    Lens
    -0.72
    Lake
    -0.69
    Tur
    -0.67
     Inquis
    -0.67
    Fear
    -0.65
    Kin
    -0.65
    element
    -0.65
    Vill
    -0.65
    POSITIVE LOGITS
    reements
    1.00
     unanimously
    0.99
     agre
    0.96
     negoti
    0.95
    ipeg
    0.93
     agreement
    0.92
    reement
    0.91
     ratified
    0.90
     negotiating
    0.89
     ratification
    0.88
    Activations Density 0.028%

    No Known Activations