© 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. 5283
    Prev
    Next
    INDEX
    Explanations

    references to the name "Raj" in various contexts

    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
    13
    +0.10
    0.5%
    373
    +0.10
    0.4%
    718
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.02
    628
    +0.10
    0.02
    232
    +0.09
    0.02
    Negative Logits
    tein
    -0.70
    ãĥĩãĤ£
    -0.65
    ABLE
    -0.60
    POS
    -0.60
     Inspector
    -0.59
     Yankee
    -0.58
    POSE
    -0.58
    çĦ
    -0.56
     Caucasian
    -0.55
     Jenner
    -0.53
    POSITIVE LOGITS
    arat
    1.05
    onian
    0.93
    aic
    0.91
    aram
    0.88
    iculture
    0.86
    aan
    0.84
    hin
    0.82
    iage
    0.82
    ivating
    0.81
    ataka
    0.80
    Activations Density 0.047%

    No Known Activations