© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5399
    Prev
    Next
    INDEX
    Explanations

    phrases related to digital media and subscription services

    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
    373
    +0.29
    1.4%
    718
    +0.09
    0.4%
    280
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.29
    -0.01
    125
    +0.09
    0.02
    508
    +0.08
    0.02
    Negative Logits
    inous
    -0.63
    (-
    -0.61
    ENE
    -0.60
    ogh
    -0.59
     Kop
    -0.59
     Haku
    -0.59
     Zot
    -0.57
    ruciating
    -0.56
    Thumbnail
    -0.56
    Advertisements
    -0.55
    POSITIVE LOGITS
    hester
    0.70
    ãĤ¦
    0.64
    illo
    0.62
    erella
    0.61
    2500
    0.59
    ¯¯¯¯
    0.58
    unity
    0.58
    usha
    0.58
    angelo
    0.57
    ettes
    0.56
    Activations Density 0.111%

    No Known Activations