© 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. 28805
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Lara Croft" and related terms in the context of video games

    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
    +0.09
    0.4%
    139
    +0.09
    0.4%
    182
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.09
    0.01
    373
    +0.09
    -0.01
    380
    +0.09
    0.01
    Negative Logits
    ADS
    -0.74
    ady
    -0.66
    inelli
    -0.66
    iate
    -0.65
    alist
    -0.65
    asters
    -0.63
    aster
    -0.63
    alties
    -0.60
    metics
    -0.60
    than
    -0.60
    POSITIVE LOGITS
     Hou
    1.03
     Hig
    0.86
    iru
    0.83
    ashi
    0.70
     Hak
    0.67
     wa
    0.66
    Ku
    0.65
    SpaceEngineers
    0.65
     Sou
    0.65
    rm
    0.64
    Activations Density 0.047%

    No Known Activations