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

    Neuronpedia

    Jacobian LensNEW
    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. 5079
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to processes, actions, and outcomes in various contexts, especially those involving decision-making and regulatory issues

    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
    373
    +0.11
    0.5%
    259
    +0.10
    0.5%
    745
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.10
    439
    +0.10
    0.06
    724
    +0.10
    0.09
    Negative Logits
    licted
    -0.68
    asm
    -0.59
     vibe
    -0.58
     enclave
    -0.56
     quart
    -0.56
    versely
    -0.54
     glim
    -0.53
     maiden
    -0.52
     trio
    -0.52
    iera
    -0.52
    POSITIVE LOGITS
     thereof
    1.14
     of
    1.13
    of
    0.96
    Of
    0.85
     Of
    0.79
     OF
    0.75
    aldehyde
    0.72
    phal
    0.72
    itism
    0.71
    Reviewer
    0.70
    Activations Density 0.746%

    No Known Activations