© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES_POST_32K-OAI
    11. 29934
    Prev
    Next
    INDEX
    Explanations

    elements related to conflicts and battles against supernatural or monstrous forces

    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
    27
    +0.10
    0.4%
    555
    +0.10
    0.4%
    517
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.10
    249
    +0.10
    0.04
    59
    +0.09
    0.05
    Negative Logits
    tesy
    -0.82
    icity
    -0.81
    utics
    -0.79
    availability
    -0.77
    iday
    -0.76
    displayText
    -0.75
    Wallet
    -0.75
    iture
    -0.74
    nington
    -0.74
    hirt
    -0.72
    POSITIVE LOGITS
     orcs
    1.23
     goblins
    1.19
     undead
    1.18
     trolls
    1.17
     monsters
    1.16
     mutated
    1.15
     demons
    1.14
     beasts
    1.11
     mutants
    1.09
     zombies
    1.09
    Activations Density 1.212%

    No Known Activations