© 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 EvalsExportsAPI 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. 29115
    Prev
    Next
    INDEX
    Explanations

    conditional statements and future actions

    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
    588
    +0.11
    0.5%
    713
    +0.11
    0.5%
    533
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    551
    +0.11
    0.15
    139
    +0.11
    0.14
    49
    +0.10
    0.13
    Negative Logits
    RANT
    -0.65
    ADS
    -0.64
     certific
    -0.64
    GROUND
    -0.62
    ãĤ®
    -0.61
    raq
    -0.60
    fax
    -0.60
     sidx
    -0.59
    VPN
    -0.59
     Compare
    -0.58
    POSITIVE LOGITS
     someday
    1.16
     soon
    1.01
     somehow
    0.98
    soon
    0.93
     eventually
    0.89
     finally
    0.79
     sooner
    0.78
     one
    0.73
    never
    0.72
     somew
    0.71
    Activations Density 0.628%

    No Known Activations