© 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 EvalsExportsinterp-engineNEWAPI 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. 4175
    Prev
    Next
    INDEX
    Explanations

    references to costs, particularly in relation to living expenses and societal 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
    339
    +0.11
    0.5%
    747
    +0.09
    0.4%
    690
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.03
    669
    +0.09
    0.02
    690
    +0.09
    0.02
    Negative Logits
    isf
    -0.90
    aha
    -0.86
    aturday
    -0.86
    limits
    -0.85
    nis
    -0.83
    ient
    -0.83
    notations
    -0.82
    achus
    -0.82
    ept
    -0.81
    \/\/
    -0.77
    POSITIVE LOGITS
     goods
    0.98
     maintaining
    0.92
     admission
    0.91
     incarcer
    0.91
     repairs
    0.89
     groceries
    0.88
     upkeep
    0.88
     acquiring
    0.85
     essentials
    0.84
     inaction
    0.83
    Activations Density 0.185%

    No Known Activations