© 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. 6014
    Prev
    Next
    INDEX
    Explanations

    structured announcements or statements about events and agreements

    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
    94
    +0.12
    0.5%
    751
    +0.11
    0.5%
    621
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.24
    640
    +0.11
    0.23
    107
    +0.09
    0.16
    Negative Logits
     sometimes
    -0.84
    omew
    -0.83
    sometimes
    -0.83
    pmwiki
    -0.80
     desperation
    -0.79
    maybe
    -0.79
     fluct
    -0.77
     fluctuations
    -0.77
    ifference
    -0.74
    acists
    -0.74
    POSITIVE LOGITS
    Tickets
    0.92
    Said
    0.85
     Includes
    0.83
     announced
    0.79
     unveiled
    0.78
    ###
    0.76
    Executive
    0.76
    announced
    0.76
     announcement
    0.76
    quartered
    0.75
    Activations Density 2.216%

    No Known Activations