© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13524
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant events, actions, or consequences

    oai_token-act-pair · gpt-3.5-turbo

    significant concepts or terms related to crises and conflict

    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
    \-
    -1.02
    gon
    -0.92
    Alert
    -0.90
    aqu
    -0.86
    Todd
    -0.85
    Studio
    -0.84
    nn
    -0.83
    ftime
    -0.81
    ocket
    -0.80
    Staff
    -0.80
    POSITIVE LOGITS
     imperialist
    1.28
     hegemony
    1.23
     bourgeoisie
    1.22
     dictatorship
    1.19
     proletariat
    1.17
     emergence
    1.16
     neoliberal
    1.15
     contradictions
    1.14
     overthrow
    1.13
     aspirations
    1.10
    Activations Density 0.356%

    No Known Activations