© 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. 28727
    Prev
    Next
    INDEX
    Explanations

    attributes and skills associated with expertise and proficiency

    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
    686
    +0.11
    0.5%
    51
    +0.11
    0.5%
    673
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.09
    51
    +0.11
    0.08
    737
    +0.10
    0.06
    Negative Logits
    ndum
    -0.66
    ãĥ´
    -0.64
    udeb
    -0.62
     è£ı
    -0.61
    rium
    -0.59
     Borough
    -0.59
    sov
    -0.58
    Balt
    -0.58
    idium
    -0.58
     Territories
    -0.57
    POSITIVE LOGITS
     negotiator
    1.03
     tact
    0.98
     manip
    0.94
     athlet
    0.90
     negotiators
    0.88
     adept
    0.85
     improvis
    0.84
     navig
    0.81
     handling
    0.78
     liar
    0.78
    Activations Density 1.350%

    No Known Activations