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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2185
    Prev
    Next
    INDEX
    Explanations

    text related to political concepts and ideologies, especially those involving economic and social structures

    oai_token-act-pair · gpt-3.5-turbo

    legal and political concepts related to Marxism and socialism

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

    No Comments

    Negative Logits
    rol
    -0.65
    OUS
    -0.64
    scene
    -0.61
    OSE
    -0.61
    OTAL
    -0.61
    ople
    -0.60
    oller
    -0.60
    OUR
    -0.59
    osc
    -0.59
     COUR
    -0.58
    POSITIVE LOGITS
     opposed
    1.15
    ylum
    1.15
    pects
    1.09
    bestos
    1.08
     evidenced
    1.04
     well
    1.03
    cription
    1.01
    pires
    1.00
    pired
    0.96
    ynchron
    0.94
    Activations Density 0.278%

    No Known Activations