© 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. 31781
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to counting or quantities

    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
    +0.12
    0.5%
    216
    +0.10
    0.5%
    347
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    -0.00
    232
    +0.10
    0.03
    288
    +0.10
    0.04
    Negative Logits
     Confeder
    -0.69
     adm
    -0.67
    joy
    -0.64
    IFE
    -0.64
    Ô
    -0.61
    ACP
    -0.61
    ITED
    -0.59
    iott
    -0.56
    riott
    -0.56
    conn
    -0.55
    POSITIVE LOGITS
    ems
    1.43
    alling
    1.23
    emic
    1.21
    alled
    1.10
    als
    1.10
    ality
    1.08
    aling
    1.06
    tering
    0.97
    aled
    0.93
    ober
    0.87
    Activations Density 0.201%

    No Known Activations