© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 7022
    Prev
    Next
    INDEX
    Explanations

    information related to business and organizational structures

    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
    229
    +0.10
    0.5%
    449
    +0.10
    0.4%
    744
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.16
    620
    +0.10
    0.01
    388
    +0.09
    0.07
    Negative Logits
    Appearances
    -0.66
    ãĥ¼ãĥ³
    -0.65
    ocene
    -0.64
     è£ıè
    -0.64
     laz
    -0.64
    çĦ
    -0.60
    ................................................................
    -0.59
    åĬ
    -0.57
    }}}
    -0.57
    astical
    -0.56
    POSITIVE LOGITS
    metics
    0.74
    ERT
    0.71
     guid
    0.68
    chnology
    0.65
     laureate
    0.63
    psey
    0.62
    agall
    0.60
    ITION
    0.60
    amily
    0.60
    istor
    0.58
    Activations Density 4.566%

    No Known Activations