© 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. 11-RES-JB
    11. 16672
    Prev
    Next
    INDEX
    Explanations

    phrases related to debates and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to significant political discussions and debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esters
    -0.89
    alan
    -0.81
    strom
    -0.77
    agues
    -0.73
    hari
    -0.73
    Studio
    -0.72
    quist
    -0.72
    quished
    -0.70
    thouse
    -0.70
    MEN
    -0.68
    POSITIVE LOGITS
     adequ
    1.35
     legality
    1.27
     fate
    1.25
     merits
    1.24
     propri
    1.22
     possibility
    1.13
     issue
    1.13
     appropri
    1.12
     feasibility
    1.10
     viability
    1.09
    Activations Density 0.232%

    No Known Activations