© 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. 10-RES_POST_32K-OAI
    11. 29078
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting-related elements such as parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    +0.11
    0.5%
    373
    +0.11
    0.5%
    557
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.11
    0.03
    627
    +0.11
    0.01
    17
    +0.11
    0.02
    Negative Logits
    Reviewer
    -0.69
     Khe
    -0.64
    zee
    -0.59
     comprom
    -0.58
    know
    -0.58
     Grail
    -0.58
     HEAD
    -0.58
    >]
    -0.57
     Gle
    -0.57
     Lilith
    -0.57
    POSITIVE LOGITS
    Ed
    1.07
    eds
    1.01
    2018
    0.89
     1986
    0.84
     1996
    0.81
     2004
    0.80
    ed
    0.79
     1999
    0.79
     1994
    0.78
     1998
    0.78
    Activations Density 0.108%

    No Known Activations