© 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. 29773
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of denial

    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
    168
    +0.11
    0.5%
    425
    +0.11
    0.5%
    690
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.11
    0.04
    360
    +0.11
    0.03
    377
    +0.10
    0.04
    Negative Logits
    =(
    -0.68
     QUEST
    -0.64
    eers
    -0.64
     Jugg
    -0.59
     Termin
    -0.58
    itives
    -0.58
    ships
    -0.58
    akeru
    -0.57
     Pros
    -0.56
     Vag
    -0.56
    POSITIVE LOGITS
     least
    1.02
     even
    0.94
    unless
    0.82
     despite
    0.81
    even
    0.78
    withstanding
    0.77
     unless
    0.76
    despite
    0.76
    except
    0.75
    albeit
    0.72
    Activations Density 0.231%

    No Known Activations