© 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. 4627
    Prev
    Next
    INDEX
    Explanations

    elements related to family and community events

    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
    363
    +0.10
    0.4%
    693
    +0.10
    0.4%
    762
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.10
    0.06
    221
    +0.10
    0.05
    698
    +0.10
    0.06
    Negative Logits
    Qual
    -0.93
    Real
    -0.88
    Gam
    -0.85
    Chart
    -0.84
    Specific
    -0.84
     Accountability
    -0.84
    STD
    -0.84
    Screen
    -0.82
    Imm
    -0.80
    Track
    -0.79
    POSITIVE LOGITS
    ensis
    1.00
    utic
    0.88
     mushrooms
    0.82
     bells
    0.80
     extraord
    0.80
     nests
    0.79
     flower
    0.78
     dancers
    0.78
     glands
    0.78
     beetle
    0.77
    Activations Density 0.883%

    No Known Activations