© 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. 30707
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty or challenges in various contexts

    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
    459
    +0.11
    0.5%
    271
    +0.11
    0.5%
    528
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.11
    0.12
    724
    +0.11
    0.13
    507
    +0.09
    0.11
    Negative Logits
     Dictionary
    -0.70
     references
    -0.69
    TextColor
    -0.68
     reprint
    -0.66
     Encyclopedia
    -0.66
     redacted
    -0.64
     hoard
    -0.63
     dictionary
    -0.63
     reference
    -0.62
     nutshell
    -0.61
    POSITIVE LOGITS
     chore
    0.73
    urred
    0.70
     undertaken
    0.68
    EP
    0.68
    intensive
    0.67
     due
    0.66
    indust
    0.66
    event
    0.66
     tasks
    0.66
     OPT
    0.65
    Activations Density 1.229%

    No Known Activations