© 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. 7-RES-JB
    11. 1911
    Prev
    Next
    INDEX
    Explanations

    words related to various strong beliefs or ideologies

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with various ideological groups and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Delivery
    -0.77
     increments
    -0.75
    Owner
    -0.64
    shown
    -0.61
    adium
    -0.60
     PROG
    -0.60
    Performance
    -0.59
     bilateral
    -0.59
     Sau
    -0.59
    ãĥ¼ãĥ³
    -0.57
    POSITIVE LOGITS
    paces
    1.36
    ervatives
    1.36
    ervative
    1.31
    hip
    1.17
    hips
    1.11
     rejoice
    1.08
    pace
    1.05
    cale
    1.01
     alike
    0.98
    peak
    0.98
    Activations Density 0.198%

    No Known Activations