© 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. 10-RES_POST_32K-OAI
    11. 32572
    Prev
    Next
    INDEX
    Explanations

    structural elements of sentences

    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
    24
    +0.11
    0.5%
    627
    +0.11
    0.5%
    750
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.11
    0.20
    43
    +0.11
    0.15
    297
    +0.10
    0.15
    Negative Logits
     varies
    -0.83
    requires
    -0.76
    pmwiki
    -0.76
     seeks
    -0.74
     employs
    -0.74
     strives
    -0.73
     applies
    -0.72
     encourages
    -0.72
     promotes
    -0.72
     undermines
    -0.71
    POSITIVE LOGITS
     hadn
    1.12
    Had
    1.09
     Was
    1.08
     Had
    1.01
    Was
    1.01
     Didn
    0.99
    didn
    0.98
     weren
    0.94
     wasn
    0.94
     knew
    0.92
    Activations Density 1.284%

    No Known Activations