© 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. 5865
    Prev
    Next
    INDEX
    Explanations

    the word "there" in various grammatical contexts

    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
    726
    +0.10
    0.5%
    521
    +0.09
    0.4%
    136
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.10
    0.05
    757
    +0.09
    0.04
    213
    +0.09
    0.03
    Negative Logits
    Rus
    -0.64
    ŃĶ
    -0.63
     enthusi
    -0.63
     Catal
    -0.60
    erity
    -0.59
    uits
    -0.58
     [|
    -0.57
     perenn
    -0.57
     Reloaded
    -0.55
     Beans
    -0.55
    POSITIVE LOGITS
    uner
    0.81
    NULL
    0.79
    inder
    0.73
    majority
    0.72
    onement
    0.70
    heny
    0.69
    ania
    0.66
    ony
    0.64
     OTHER
    0.64
    zero
    0.64
    Activations Density 0.093%

    No Known Activations