© 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. 4264
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, particularly those associated with notable individuals or entities

    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
    421
    +0.15
    0.7%
    377
    +0.14
    0.7%
    459
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.03
    232
    +0.14
    0.03
    316
    +0.12
    0.02
    Negative Logits
    riage
    -0.78
    dain
    -0.63
    ÅŁ
    -0.62
    score
    -0.59
    pub
    -0.59
    ÄŁ
    -0.58
    teen
    -0.56
     fert
    -0.56
     spaced
    -0.55
    Fram
    -0.55
    POSITIVE LOGITS
    coe
    0.92
    idation
    0.88
    ocaust
    0.88
    isf
    0.87
    ories
    0.86
    ocal
    0.79
    idity
    0.79
    etta
    0.79
    bite
    0.79
    gow
    0.78
    Activations Density 0.106%

    No Known Activations