© 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. 32134
    Prev
    Next
    INDEX
    Explanations

    variations of the prefix "ro" and its related forms

    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
    0
    +0.10
    0.5%
    174
    +0.10
    0.5%
    352
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.10
    -0.00
    232
    +0.10
    0.05
    404
    +0.08
    0.04
    Negative Logits
    ĸļ
    -0.70
    ģ«
    -0.69
    rine
    -0.69
    AGES
    -0.67
    borg
    -0.67
    Cath
    -0.65
    Wire
    -0.65
    cens
    -0.64
     Birds
    -0.63
    DAY
    -0.63
    POSITIVE LOGITS
    aching
    0.84
    isers
    0.80
    vernment
    0.77
    edy
    0.76
    itiveness
    0.75
    ittees
    0.75
    casting
    0.73
    ittee
    0.71
    isal
    0.71
    ition
    0.70
    Activations Density 0.418%

    No Known Activations