© 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. 11-RES-JB
    11. 596
    Prev
    Next
    INDEX
    Explanations

    negative descriptions of certain ideologies or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    negative perceptions and descriptors of ideologies, particularly related to Islam and associated ideologies

    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
    adelphia
    -0.75
    ventory
    -0.72
     Delivery
    -0.72
    glers
    -0.71
    DAQ
    -0.71
     Garr
    -0.70
    Delivery
    -0.69
    burse
    -0.67
    gomery
    -0.66
    itures
    -0.65
    POSITIVE LOGITS
     nihil
    1.24
     bigotry
    1.24
     fascists
    1.23
     fascist
    1.22
     fascism
    1.21
     atheism
    1.20
     totalitarian
    1.20
     heresy
    1.19
     intoler
    1.18
     reactionary
    1.18
    Activations Density 0.851%

    No Known Activations