© 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. 5513
    Prev
    Next
    INDEX
    Explanations

    phrases indicating various types of experiences or states involving the word "a" coupled with emotional or situational descriptors

    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
    666
    +0.13
    0.6%
    144
    +0.11
    0.5%
    601
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.13
    0.08
    608
    +0.11
    0.07
    408
    +0.10
    0.07
    Negative Logits
    arning
    -0.78
    oway
    -0.64
    ensing
    -0.64
    UC
    -0.60
    quartered
    -0.60
     ILCS
    -0.59
    ieth
    -0.59
    english
    -0.58
     currently
    -0.58
     promise
    -0.58
    POSITIVE LOGITS
     conversations
    0.92
     conversation
    0.89
     Conversation
    0.86
     intercourse
    0.85
     fun
    0.78
     discussions
    0.77
     affair
    0.77
    iphany
    0.73
     discussion
    0.72
     fruitful
    0.71
    Activations Density 0.584%

    No Known Activations