© 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 EvalsExportsinterp-engineNEWAPI 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. 7780
    Prev
    Next
    INDEX
    Explanations

    recurring themes and terms used to discuss various subjects, including music, plants, websites, diseases, and products

    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
    139
    +0.12
    0.6%
    477
    +0.10
    0.5%
    757
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.12
    0.10
    288
    +0.10
    0.11
    563
    +0.09
    0.09
    Negative Logits
    soever
    -0.75
    ":-
    -0.71
    ..................
    -0.69
    Unknown
    -0.67
    annie
    -0.66
    izu
    -0.65
     bombshell
    -0.65
    Huh
    -0.63
    Yep
    -0.63
    ————
    -0.63
    POSITIVE LOGITS
     performs
    0.97
     undergo
    0.94
     excel
    0.93
     itself
    0.87
     also
    0.86
     utilizes
    0.84
     conducts
    0.83
     lacks
    0.82
     employs
    0.80
     behaves
    0.79
    Activations Density 1.066%

    No Known Activations