© 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. 4936
    Prev
    Next
    INDEX
    Explanations

    references to religious figures and beliefs, particularly related to Christianity

    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
    192
    +0.09
    0.4%
    108
    +0.08
    0.4%
    264
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.09
    0.03
    350
    +0.08
    0.02
    247
    +0.08
    0.02
    Negative Logits
    acle
    -0.71
    abol
    -0.70
    rike
    -0.70
    staking
    -0.66
    advertising
    -0.63
    enary
    -0.63
    fun
    -0.61
    bike
    -0.61
    isks
    -0.61
    lvl
    -0.61
    POSITIVE LOGITS
     Lumpur
    0.68
     Latter
    0.63
     Picture
    0.58
     Univ
    0.58
     Messiah
    0.57
     International
    0.56
     wa
    0.55
     IU
    0.55
     Evangel
    0.54
     Method
    0.54
    Activations Density 0.181%

    No Known Activations