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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 17496
    Prev
    Next
    INDEX
    Explanations

    political affiliations and stances

    oai_token-act-pair · gpt-3.5-turbo

    statistical data related to political party affiliation and public opinion

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

    No Comments

    Negative Logits
     plates
    -0.59
    authent
    -0.57
    bugs
    -0.56
    launch
    -0.56
    ss
    -0.54
     sandbox
    -0.53
     rituals
    -0.53
     ethos
    -0.53
     heed
    -0.52
     extradition
    -0.52
    POSITIVE LOGITS
     averaging
    0.97
     averaged
    0.92
    verages
    0.91
     Gallup
    0.85
     Percentage
    0.85
    adjusted
    0.83
     averages
    0.83
    average
    0.82
     Adjusted
    0.82
    Average
    0.81
    Activations Density 2.059%

    No Known Activations