© 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. 32041
    Prev
    Next
    INDEX
    Explanations

    mentions of "stretch goals" in a campaign context

    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
    459
    +0.16
    0.7%
    582
    +0.12
    0.5%
    450
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.16
    0.02
    450
    +0.12
    0.02
    592
    +0.12
    0.02
    Negative Logits
    nect
    -0.88
    ufact
    -0.82
    eer
    -0.75
    vernment
    -0.75
    eers
    -0.75
    eering
    -0.72
    ienced
    -0.72
    ité
    -0.69
    ãĥ£
    -0.69
    alty
    -0.67
    POSITIVE LOGITS
    opian
    0.82
     lim
    0.80
     Goals
    0.78
     cred
    0.72
     guiActiveUnfocused
    0.71
     stretched
    0.68
    bean
    0.65
     goals
    0.64
    aints
    0.64
    ĸļ
    0.64
    Activations Density 0.206%

    No Known Activations