© 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. 28313
    Prev
    Next
    INDEX
    Explanations

    references to dimensions and realms in a hypothetical or scientific context

    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
    288
    +0.13
    0.6%
    662
    +0.10
    0.4%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.04
    737
    +0.10
    0.02
    435
    +0.10
    0.02
    Negative Logits
    etsk
    -0.79
    bats
    -0.77
    enz
    -0.75
    ortium
    -0.74
    onica
    -0.73
    essee
    -0.73
    pta
    -0.72
    die
    -0.72
    enza
    -0.71
    yright
    -0.69
    POSITIVE LOGITS
    ality
    1.17
    ally
    0.96
    als
    0.85
    naire
    0.84
    arium
    0.83
     shif
    0.82
    ALLY
    0.80
     guiActiveUnfocused
    0.76
     perpendicular
    0.73
     Nept
    0.73
    Activations Density 0.148%

    No Known Activations