Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16890
    Prev
    Next
    INDEX
    Explanations

    references to various political ideologies and theories

    oai_token-act-pair · gpt-3.5-turbo

    references to ideologies and theories related to Marxism and political philosophy

    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
    emouth
    -0.74
    OPLE
    -0.74
     emergencies
    -0.74
    imity
    -0.72
    watching
    -0.69
     parking
    -0.66
    woman
    -0.66
     Parking
    -0.65
     istg
    -0.64
    enged
    -0.64
    POSITIVE LOGITS
     variants
    1.22
     variations
    1.17
     modified
    1.13
     variant
    1.10
     derivative
    1.06
     adapted
    1.02
     similarities
    1.02
     versions
    1.01
     equivalents
    1.00
     variation
    0.99
    Activations Density 1.180%

    No Known Activations