© 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. 8-RES_POST_32K-OAI
    11. 4413
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate purpose or intention

    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
    37
    +0.10
    0.5%
    580
    +0.10
    0.5%
    251
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    580
    +0.10
    0.10
    608
    +0.10
    0.14
    256
    +0.10
    0.08
    Negative Logits
    lex
    -0.70
    bats
    -0.65
    cloth
    -0.64
    uberty
    -0.62
    batch
    -0.61
     moss
    -0.59
     Britann
    -0.57
     aval
    -0.57
     bruises
    -0.56
    cephal
    -0.56
    POSITIVE LOGITS
     goal
    1.93
     purpose
    1.79
     aim
    1.72
     objectives
    1.71
     goals
    1.68
     objective
    1.64
     aims
    1.54
    goal
    1.52
     Purpose
    1.51
     purposes
    1.40
    Activations Density 6.432%

    No Known Activations