© 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. 5532
    Prev
    Next
    INDEX
    Explanations

    phrases indicating motion or transition into a state or place

    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
    730
    +0.11
    0.5%
    573
    +0.10
    0.5%
    354
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.11
    0.06
    608
    +0.10
    0.05
    218
    +0.10
    0.04
    Negative Logits
    bourg
    -0.66
    burgh
    -0.64
    terday
    -0.62
    loo
    -0.61
    ovan
    -0.60
    Bey
    -0.60
    ittle
    -0.59
    don
    -0.58
    gram
    -0.55
    ogyn
    -0.55
    POSITIVE LOGITS
     position
    0.92
     recess
    0.79
     positions
    0.79
    sleep
    0.74
     darkness
    0.74
     hypers
    0.73
     bed
    0.72
    Position
    0.69
     hiber
    0.69
     ambush
    0.69
    Activations Density 0.188%

    No Known Activations