© 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. 7224
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving and responding to communications or inquiries

    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
    71
    +0.13
    0.6%
    254
    +0.12
    0.5%
    489
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    646
    +0.13
    0.06
    183
    +0.12
    0.05
    357
    +0.12
    0.06
    Negative Logits
     notwithstanding
    -0.68
    erness
    -0.68
    tsky
    -0.66
     Hist
    -0.62
     Underground
    -0.62
     econom
    -0.61
     Surviv
    -0.60
     Cure
    -0.60
     Recon
    -0.58
     segreg
    -0.58
    POSITIVE LOGITS
     requests
    1.41
     inquiries
    1.30
     complaints
    1.20
     emails
    1.15
     queries
    1.13
     calls
    1.09
     request
    1.08
    mails
    1.04
     invitation
    1.02
     enqu
    1.01
    Activations Density 1.122%

    No Known Activations