© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 5569
    Prev
    Next
    INDEX
    Explanations

    political ideologies and affiliations, particularly focused on socialism and related terms

    oai_token-act-pair · gpt-3.5-turbo

    ideological terms related to socialism and its critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -1.07
    ptin
    -0.90
    llular
    -0.88
    pai
    -0.88
    krit
    -0.88
    hower
    -0.86
    sure
    -0.86
    cellent
    -0.84
    dropping
    -0.83
    iard
    -0.82
    POSITIVE LOGITS
     tendencies
    1.25
     ideals
    1.12
     strongh
    1.10
     ideology
    1.08
     stronghold
    1.05
     movement
    1.02
     manifesto
    1.01
     zeal
    1.00
     dogma
    1.00
     ferv
    1.00
    Activations Density 0.177%

    No Known Activations