© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5272
    Prev
    Next
    INDEX
    Explanations

    instances of the term "breach" and related concepts

    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
    88
    +0.11
    0.5%
    183
    +0.11
    0.5%
    220
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.03
    271
    +0.11
    0.02
    540
    +0.11
    0.02
    Negative Logits
    ibur
    -0.81
     stag
    -0.76
    uana
    -0.72
    lee
    -0.70
    aiden
    -0.69
    eday
    -0.68
    elled
    -0.68
     Belt
    -0.67
    irez
    -0.66
    puff
    -0.66
    POSITIVE LOGITS
    ingly
    0.83
     breach
    0.81
     breaches
    0.80
    terness
    0.78
     Breach
    0.75
    ionage
    0.74
    hold
    0.72
    hent
    0.66
    chnology
    0.65
    Timeout
    0.65
    Activations Density 0.107%

    No Known Activations