© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4924
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "of" combined with possessive or quantifying terms

    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
    60
    +0.14
    0.6%
    393
    +0.11
    0.5%
    559
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.05
    393
    +0.11
    0.05
    611
    +0.11
    0.04
    Negative Logits
    Mex
    -0.75
    agy
    -0.67
    idad
    -0.63
    anty
    -0.63
    aceae
    -0.61
     remission
    -0.61
     derog
    -0.60
    oulder
    -0.60
    icides
    -0.60
    eteenth
    -0.60
    POSITIVE LOGITS
    initialized
    0.84
     std
    0.84
     Users
    0.81
     TEST
    0.81
     FIG
    0.78
     course
    0.77
     Configuration
    0.77
     your
    0.74
     Files
    0.74
     Intent
    0.74
    Activations Density 0.269%

    No Known Activations