© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4643
    Prev
    Next
    INDEX
    Explanations

    phrases related to interpretation and context of statements or beliefs

    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
    320
    +0.11
    0.5%
    486
    +0.10
    0.5%
    756
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.09
    718
    +0.10
    0.12
    512
    +0.09
    0.10
    Negative Logits
    Reviewer
    -0.83
    ellen
    -0.68
     undefeated
    -0.65
     cz
    -0.64
    uries
    -0.62
    bable
    -0.61
     underrated
    -0.60
     thrive
    -0.59
    oner
    -0.58
    hess
    -0.58
    POSITIVE LOGITS
     referring
    1.22
     referencing
    1.02
     refers
    0.92
     merely
    0.89
     implying
    0.88
     meant
    0.87
     refer
    0.80
     signify
    0.80
     mean
    0.77
     reference
    0.76
    Activations Density 4.420%

    No Known Activations