© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5021
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and expectations related to actions or events

    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
    603
    +0.14
    0.6%
    218
    +0.12
    0.5%
    139
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.14
    0.15
    551
    +0.12
    0.14
    49
    +0.11
    0.12
    Negative Logits
    76561
    -0.79
     Restrict
    -0.76
     restricting
    -0.74
     examining
    -0.71
     assigning
    -0.71
     gau
    -0.70
     analyzing
    -0.69
     investigating
    -0.69
     enforcing
    -0.69
     regulating
    -0.67
    POSITIVE LOGITS
     died
    1.12
     perished
    1.11
     perish
    1.09
     overshadow
    1.06
     cameo
    1.04
     die
    1.01
    die
    0.99
     emerge
    0.94
     accompany
    0.92
     disappeared
    0.92
    Activations Density 1.163%

    No Known Activations