© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5685
    Prev
    Next
    INDEX
    Explanations

    instances of the word "back" in various contexts

    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
    678
    +0.10
    0.4%
    161
    +0.10
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.10
    0.04
    619
    +0.10
    0.04
    424
    +0.09
    0.03
    Negative Logits
    aucus
    -0.62
    dylib
    -0.60
     delegation
    -0.54
     Unicorn
    -0.54
    ery
    -0.53
     donation
    -0.53
     donated
    -0.52
    ertation
    -0.52
    ptions
    -0.52
     technicians
    -0.51
    POSITIVE LOGITS
     downwards
    0.82
     thro
    0.79
     down
    0.78
     toward
    0.78
     towards
    0.78
     onto
    0.76
     downstairs
    0.76
     downward
    0.74
     onwards
    0.73
     awake
    0.70
    Activations Density 0.094%

    No Known Activations