© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 26964
    Prev
    Next
    INDEX
    Explanations

    references to major corporations and financial transactions in the context of business and acquisitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    434
    +0.10
    0.4%
    299
    +0.09
    0.4%
    99
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.10
    0.08
    506
    +0.09
    0.06
    288
    +0.09
    0.08
    Negative Logits
    geries
    -0.86
    qqa
    -0.80
    ydia
    -0.79
    irlf
    -0.75
    pmwiki
    -0.72
    ourced
    -0.71
    arij
    -0.71
    inav
    -0.71
    soDeliveryDate
    -0.71
    roxy
    -0.68
    POSITIVE LOGITS
     Corp
    1.25
     Inc
    1.13
     Holdings
    1.08
     subsidiary
    1.01
     Corporation
    1.00
     CEO
    0.99
     Stores
    0.98
     Company
    0.95
     shareholders
    0.95
     Ltd
    0.93
    Activations Density 0.935%

    No Known Activations