© 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. 10-RES_POST_32K-OAI
    6. 29621
    Prev
    Next
    INDEX
    Explanations

    discussions related to influence and sponsorship in content creation

    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
    373
    +0.13
    0.6%
    647
    +0.10
    0.4%
    126
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.13
    -0.03
    534
    +0.10
    0.01
    44
    +0.10
    0.01
    Negative Logits
    eus
    -0.68
     Rousse
    -0.63
    argon
    -0.61
    Xi
    -0.59
    opathy
    -0.59
     Nieto
    -0.59
    İĭ
    -0.59
    umenthal
    -0.58
    wealth
    -0.58
    forth
    -0.56
    POSITIVE LOGITS
     Flavoring
    0.71
    lins
    0.66
     rounding
    0.65
    Reviewer
    0.64
     evaluations
    0.63
    ories
    0.63
    rounded
    0.60
    omed
    0.59
     thousands
    0.59
    ateurs
    0.58
    Activations Density 0.295%

    No Known Activations