© 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. 4508
    Prev
    Next
    INDEX
    Explanations

    words related to historical figures and their titles

    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
    6
    +0.12
    0.6%
    284
    +0.09
    0.4%
    63
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.04
    284
    +0.09
    0.03
    52
    +0.09
    0.03
    Negative Logits
    sembly
    -0.91
    anwhile
    -0.88
     unden
    -0.84
    owship
    -0.82
     notor
    -0.80
     encount
    -0.78
    etheless
    -0.77
     challeng
    -0.75
     contrace
    -0.75
    ailability
    -0.74
    POSITIVE LOGITS
    çļĦ
    1.29
    ãĤĴ
    1.28
    ãģ®
    1.25
    ãģķ
    1.24
    ãģ§
    1.20
    ãĢĮ
    1.18
    ãģĻ
    1.18
    ãģ¨
    1.17
    ãĢĤ
    1.17
    ãģĹ
    1.16
    Activations Density 0.120%

    No Known Activations