© 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. 4781
    Prev
    Next
    INDEX
    Explanations

    URLs and links related to social media and web content

    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
    218
    +0.11
    0.5%
    136
    +0.10
    0.5%
    297
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    140
    +0.11
    0.03
    136
    +0.10
    0.03
    311
    +0.10
    0.00
    Negative Logits
    ICAN
    -0.72
     Inspection
    -0.68
    cius
    -0.68
     Nicotine
    -0.67
    ©¶æ¥µ
    -0.63
     Examination
    -0.62
     textbook
    -0.61
     Celestial
    -0.61
     Dying
    -0.61
     Dracula
    -0.60
    POSITIVE LOGITS
     @
    0.97
    intent
    0.90
     (@
    0.87
     "@
    0.86
     hashtag
    0.83
    @
    0.82
    uters
    0.80
    twitch
    0.79
     hasht
    0.76
    twitter
    0.73
    Activations Density 0.450%

    No Known Activations