© 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. 4-RES-JB
    11. 15181
    Prev
    Next
    INDEX
    Explanations

    mentions of political labels like 'liberals' and 'conservatives'

    oai_token-act-pair · gpt-3.5-turbo

    references to liberals and their associated concepts or values

    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
    Delivery
    -0.70
    inventoryQuantity
    -0.67
     submission
    -0.64
     increments
    -0.61
     circumstances
    -0.59
    wise
    -0.58
    Owner
    -0.58
    Account
    -0.58
     domain
    -0.58
     Territories
    -0.57
    POSITIVE LOGITS
    ervatives
    1.36
    aurus
    1.32
    paces
    1.32
    ervative
    1.30
    hip
    1.06
    chool
    1.02
    mith
    1.02
    hips
    1.00
    ongs
    0.92
    heet
    0.92
    Activations Density 0.082%

    No Known Activations