© 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. 4472
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional experiences and memories related to social interactions

    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
    373
    +0.87
    8.3%
    447
    +0.23
    2.2%
    480
    +0.08
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.87
    0.86
    138
    +0.23
    0.83
    64
    +0.08
    -0.27
    Negative Logits
    etheless
    -0.39
    Elsewhere
    -0.35
    ?).
    -0.31
     sqor
    -0.31
     therein
    -0.31
     thereof
    -0.30
     thereto
    -0.30
    itto
    -0.30
    atto
    -0.29
    0002
    -0.29
    POSITIVE LOGITS
     people
    0.28
     amazing
    0.27
     ÂŃ
    0.26
     incredible
    0.26
    phal
    0.26
     animal
    0.25
     emergency
    0.25
     human
    0.25
     astroph
    0.25
     energy
    0.25
    Activations Density 36.301%

    No Known Activations