© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4875
    Prev
    Next
    INDEX
    Explanations

    structured data or code-like elements

    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
    314
    +0.12
    0.5%
    513
    +0.10
    0.5%
    529
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.12
    0.08
    497
    +0.10
    0.04
    160
    +0.10
    0.07
    Negative Logits
     recy
    -0.59
     enriched
    -0.55
    stuff
    -0.54
     stunts
    -0.54
     headquartered
    -0.53
     pancakes
    -0.52
     incompet
    -0.52
     organising
    -0.51
    rising
    -0.51
     retard
    -0.51
    POSITIVE LOGITS
     Ibid
    1.01
    ļéĨĴ
    1.00
    DragonMagazine
    0.85
     Moroc
    0.82
    %%%%
    0.82
    Merit
    0.74
    OTAL
    0.74
     Mehran
    0.72
    Advertisements
    0.71
    ################################
    0.69
    Activations Density 0.836%

    No Known Activations