© 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. 7218
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreement or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    words related to consensus and decision-making

    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
     detriment
    -0.72
     predators
    -0.68
    HOME
    -0.68
     harvesting
    -0.66
     stabilization
    -0.65
     fragmentation
    -0.64
     stability
    -0.63
     interference
    -0.63
     occupancy
    -0.62
     starvation
    -0.62
    POSITIVE LOGITS
    okingly
    1.13
    ighed
    1.03
    answered
    1.01
    urred
    1.00
    jected
    1.00
    wrote
    0.97
    ued
    0.96
    itled
    0.94
    oled
    0.94
     Cosponsors
    0.93
    Activations Density 0.143%

    No Known Activations