© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 7794
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or places named "Cape."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Cape"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naires
    -0.76
    arial
    -0.72
    swer
    -0.71
    amine
    -0.71
    NESS
    -0.69
    atically
    -0.68
    ÑĮ
    -0.66
    utterstock
    -0.66
    edy
    -0.64
    agi
    -0.64
    POSITIVE LOGITS
    lla
    1.19
    llan
    1.18
     Cod
    1.07
     Canaveral
    1.01
     Coral
    0.96
     Colony
    0.90
     Coast
    0.90
     Town
    0.84
    lli
    0.81
    reon
    0.79
    Activations Density 0.027%

    No Known Activations