© 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. 8-RES_POST_32K-OAI
    6. 4633
    Prev
    Next
    INDEX
    Explanations

    references to rankings or positions

    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
    500
    +0.10
    0.5%
    712
    +0.10
    0.5%
    497
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.15
    49
    +0.10
    0.09
    566
    +0.09
    0.07
    Negative Logits
     UID
    -0.72
    sense
    -0.65
    meet
    -0.59
     Annotations
    -0.59
    wow
    -0.57
    UID
    -0.56
     Organizations
    -0.54
    Online
    -0.53
    ONE
    -0.53
     Secondly
    -0.53
    POSITIVE LOGITS
     theirs
    0.91
     hers
    0.90
     likewise
    0.84
    ãĥĺ
    0.66
    inery
    0.64
    yang
    0.60
     similarly
    0.59
    iry
    0.59
     TBA
    0.56
     haz
    0.55
    Activations Density 3.260%

    No Known Activations