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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21361
    Prev
    Next
    INDEX
    Explanations

    directional terms indicating locations, specifically focusing on east and west

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical directions, specifically 'east' and 'west'

    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
    argon
    -0.77
    utable
    -0.73
    Owner
    -0.73
     reluct
    -0.73
    abulary
    -0.72
     istg
    -0.71
     confir
    -0.71
    ASED
    -0.71
    TABLE
    -0.70
    inventoryQuantity
    -0.70
    POSITIVE LOGITS
    ward
    1.35
    wards
    1.15
    side
    1.14
     coast
    1.00
     hemisphere
    0.96
    urst
    0.86
     west
    0.86
    west
    0.85
    bound
    0.84
     wing
    0.79
    Activations Density 0.014%

    No Known Activations