© 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. 31088
    Prev
    Next
    INDEX
    Explanations

    iterative phrases related to agreements or subscriptions

    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
    146
    +0.11
    0.5%
    733
    +0.10
    0.5%
    736
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.02
    6
    +0.10
    0.03
    733
    +0.10
    0.01
    Negative Logits
    iciency
    -0.75
    otype
    -0.73
     Bord
    -0.69
    otypes
    -0.69
    ortium
    -0.68
    Imp
    -0.67
    pecting
    -0.65
    perty
    -0.65
    oeuv
    -0.63
    incial
    -0.63
    POSITIVE LOGITS
     Hilbert
    0.71
     landsl
    0.64
     domains
    0.62
     illegitimate
    0.61
    terms
    0.61
    ussia
    0.60
     violates
    0.59
     strives
    0.58
    },"
    0.58
     landing
    0.57
    Activations Density 0.183%

    No Known Activations