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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 29138
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Mall" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    526
    +0.13
    0.6%
    288
    +0.13
    0.6%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.03
    526
    +0.13
    0.00
    444
    +0.11
    0.01
    Negative Logits
    dit
    -0.81
    vich
    -0.67
     Typhoon
    -0.63
     charism
    -0.63
    SHIP
    -0.61
    itably
    -0.61
     Daisy
    -0.60
     Corm
    -0.59
     Jays
    -0.58
     Liu
    -0.58
    POSITIVE LOGITS
    adium
    1.09
    itect
    1.09
    ards
    1.03
    opping
    1.02
    oppers
    0.99
    esi
    0.97
    ard
    0.94
    eson
    0.91
    oppable
    0.91
    ocks
    0.91
    Activations Density 0.122%

    No Known Activations