© 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 EvalsExportsinterp-engineNEWAPI 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. 31181
    Prev
    Next
    INDEX
    Explanations

    the word "one" in various contexts, indicating a focus on singularity or uniqueness

    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
    320
    +0.13
    0.6%
    304
    +0.11
    0.5%
    397
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.13
    0.04
    133
    +0.11
    0.04
    533
    +0.09
    0.04
    Negative Logits
    SpaceEngineers
    -0.68
    xon
    -0.65
    hoff
    -0.63
    }:
    -0.62
     srfAttach
    -0.60
    rontal
    -0.60
    Appearance
    -0.58
    oho
    -0.56
    chid
    -0.56
    oba
    -0.55
    POSITIVE LOGITS
     whose
    1.12
     which
    1.10
     that
    1.08
    that
    0.89
     wherein
    0.89
    which
    0.87
    whose
    0.85
     thats
    0.83
     THAT
    0.82
     requiring
    0.82
    Activations Density 0.106%

    No Known Activations