© 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 EvalsExportsinterp-engineNEWAPI 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. 31543
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or names, particularly those containing "Khal" or "Jal"

    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
    514
    +0.12
    0.5%
    201
    +0.10
    0.5%
    749
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.03
    314
    +0.10
    0.00
    232
    +0.10
    0.02
    Negative Logits
    %%
    -0.74
    hift
    -0.71
     Sacrament
    -0.71
    ramer
    -0.69
    âĦ¢:
    -0.69
    manship
    -0.66
     Grail
    -0.65
    CLOSE
    -0.63
    hler
    -0.63
     stal
    -0.63
    POSITIVE LOGITS
    ifa
    1.16
    opy
    0.93
    IFA
    0.84
    azard
    0.84
    pmwiki
    0.82
    asar
    0.81
    merga
    0.80
    jab
    0.80
    pless
    0.77
    endar
    0.76
    Activations Density 0.124%

    No Known Activations