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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5440
    Prev
    Next
    INDEX
    Explanations

    terms related to noble houses and their roles in a fantasy setting

    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
    314
    +0.14
    0.6%
    419
    +0.11
    0.5%
    662
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.14
    325
    +0.11
    0.10
    99
    +0.10
    0.07
    Negative Logits
    Todd
    -0.82
     surv
    -0.75
     obesity
    -0.70
     Fitness
    -0.69
    Jr
    -0.69
     absentee
    -0.67
     elig
    -0.67
     cardio
    -0.67
    FK
    -0.67
     disability
    -0.66
    POSITIVE LOGITS
    maid
    1.00
    god
    0.99
    wright
    0.99
    sword
    0.97
     goddess
    0.96
    chant
    0.94
     deity
    0.93
    seed
    0.93
    keeper
    0.93
     priests
    0.91
    Activations Density 1.277%

    No Known Activations