© 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. 6426
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals or entities with the name "Rom" or similar variations

    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
    522
    +0.11
    0.5%
    9
    +0.10
    0.5%
    232
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.02
    659
    +0.10
    0.01
    597
    +0.09
    0.01
    Negative Logits
     ramps
    -0.64
     attendant
    -0.64
     Rouhani
    -0.63
     traveller
    -0.59
     disclaimer
    -0.57
     whiff
    -0.57
    lift
    -0.56
     dams
    -0.56
    eers
    -0.56
    CRIP
    -0.55
    POSITIVE LOGITS
    antically
    1.34
    antics
    1.30
    antic
    1.21
    ulus
    1.14
    aji
    1.10
    anes
    1.09
    ancing
    1.05
    agn
    1.05
    agna
    1.04
    ijn
    1.04
    Activations Density 0.036%

    No Known Activations