© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 6741
    Prev
    Next
    INDEX
    Explanations

    action words related to communication and production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    314
    +0.20
    0.9%
    38
    +0.09
    0.4%
    325
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.14
    314
    +0.09
    -0.01
    140
    +0.09
    0.09
    Negative Logits
     davidjl
    -0.63
     cinem
    -0.62
     constitu
    -0.62
     Hurricanes
    -0.61
     Monstrous
    -0.61
     Purple
    -0.58
     Aven
    -0.58
     Sapp
    -0.56
     Collins
    -0.56
     WOM
    -0.55
    POSITIVE LOGITS
    ings
    1.80
    ables
    1.63
    able
    1.58
    ers
    1.49
    ability
    1.47
    downs
    1.35
    aways
    1.32
    outs
    1.30
    away
    1.26
    ances
    1.26
    Activations Density 2.142%

    No Known Activations