© 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. 4511
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and financial matters

    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
    599
    +0.14
    0.6%
    561
    +0.12
    0.5%
    564
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.14
    0.01
    330
    +0.12
    0.00
    756
    +0.10
    -0.00
    Negative Logits
    ubuntu
    -0.81
    ess
    -0.80
    esses
    -0.78
    osaurus
    -0.77
    ã
    -0.76
    ospace
    -0.76
    ancies
    -0.74
    ovember
    -0.72
    otle
    -0.71
    acs
    -0.70
    POSITIVE LOGITS
     Currency
    1.39
     Marketable
    0.80
    BuyableInstoreAndOnline
    0.80
    Buyable
    0.78
     Belt
    0.78
     Commerce
    0.76
     Treasury
    0.75
     Amount
    0.74
     Casino
    0.73
     currency
    0.72
    Activations Density 0.010%

    No Known Activations