© 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. 10-RES-JB
    11. 14006
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and ideological concepts, particularly socialism and capitalism

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms associated with social and political theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovember
    -0.85
    cheat
    -0.78
    osponsors
    -0.72
    OTOS
    -0.70
     OPS
    -0.66
     ransomware
    -0.64
    Tips
    -0.64
     Rounds
    -0.62
     spoof
    -0.61
    Todd
    -0.61
    POSITIVE LOGITS
     embodied
    1.13
    ivist
    1.08
    uality
    1.04
     whereby
    1.03
     mund
    1.01
     thereof
    1.00
     manifested
    1.00
     inherent
    0.96
    ativity
    0.96
    lessness
    0.95
    Activations Density 0.374%

    No Known Activations