© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5838
    Prev
    Next
    INDEX
    Explanations

    references to links or URLs

    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
    424
    +0.11
    0.5%
    426
    +0.11
    0.5%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.11
    0.01
    107
    +0.11
    0.01
    445
    +0.09
    0.01
    Negative Logits
     Nicaragua
    -0.61
    ient
    -0.60
     Kut
    -0.59
     situ
    -0.59
     habit
    -0.58
     Mazda
    -0.58
    etheless
    -0.57
     sacrific
    -0.56
     gain
    -0.56
     asymm
    -0.56
    POSITIVE LOGITS
    DEBUG
    0.98
    WARN
    0.91
    INFO
    0.89
    ERROR
    0.86
    RESULTS
    0.81
    illin
    0.79
    WARNING
    0.74
     Keller
    0.73
    ERA
    0.71
    âĸĵ
    0.68
    Activations Density 0.017%

    No Known Activations