© 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 EvalsExportsAPI 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. 2-RES-JB
    11. 22561
    Prev
    Next
    INDEX
    Explanations

    references to the Communist Party

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Communist Party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MAT
    -0.68
    angelo
    -0.68
     Drake
    -0.68
    VILLE
    -0.66
     McF
    -0.66
     Yellowstone
    -0.65
     Monroe
    -0.65
    TEXTURE
    -0.65
     bolts
    -0.64
     Snyder
    -0.63
    POSITIVE LOGITS
    alion
    1.01
     organising
    0.92
     strugg
    0.81
    emetery
    0.79
    ority
    0.79
     planner
    0.79
     communists
    0.74
     learnt
    0.74
     hierarchy
    0.74
     dictatorship
    0.73
    Activations Density 0.036%

    No Known Activations