© 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. 32464
    Prev
    Next
    INDEX
    Explanations

    references to the term "Crusader" and its variations, as well as concepts related to conflict and division

    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
    373
    +0.11
    0.5%
    99
    +0.11
    0.5%
    143
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.05
    659
    +0.11
    0.02
    526
    +0.10
    -0.01
    Negative Logits
    ele
    -0.73
    orage
    -0.69
    dit
    -0.68
    eus
    -0.68
    electric
    -0.67
    BOOK
    -0.67
    ery
    -0.63
    hap
    -0.63
    ĪĴ
    -0.61
     Squirrel
    -0.60
    POSITIVE LOGITS
    aders
    1.49
    ading
    1.23
    adia
    1.13
    ader
    1.09
    adian
    1.01
    ades
    0.98
    aded
    0.94
    aken
    0.86
    annon
    0.84
    riors
    0.83
    Activations Density 0.248%

    No Known Activations