© 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. 8-RES_POST_32K-OAI
    11. 7269
    Prev
    Next
    INDEX
    Explanations

    terms related to mental and emotional well-being scores or metrics

    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
    735
    +0.10
    0.4%
    198
    +0.10
    0.4%
    390
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.10
    0.01
    652
    +0.10
    0.01
    611
    +0.09
    0.01
    Negative Logits
    ards
    -0.78
    cks
    -0.77
    acl
    -0.77
    ographically
    -0.76
    ardless
    -0.74
    istically
    -0.74
    entially
    -0.74
    oS
    -0.73
    icas
    -0.73
    lly
    -0.72
    POSITIVE LOGITS
     Shroud
    0.69
     recess
    0.68
     Quran
    0.65
     shroud
    0.63
     conduit
    0.61
     Blaze
    0.60
     Babel
    0.60
    atomic
    0.59
     Blaz
    0.58
    rament
    0.58
    Activations Density 0.093%

    No Known Activations