Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 6-RES_POST_32K-OAI
    6. 4221
    Prev
    Next
    INDEX
    Explanations

    adverbs that convey the degree or manner of an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_6.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    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
    163
    +0.13
    0.6%
    151
    +0.13
    0.6%
    284
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.13
    0.06
    307
    +0.13
    0.04
    45
    +0.10
    0.03
    Negative Logits
    angular
    -0.87
    idious
    -0.78
     filings
    -0.74
    peria
    -0.73
    overs
    -0.72
    rules
    -0.68
     Tycoon
    -0.68
    pick
    -0.67
    CU
    -0.66
    ulators
    -0.66
    POSITIVE LOGITS
     Atmosp
    0.73
    ienced
    0.73
     understatement
    0.72
    ufact
    0.71
    asty
    0.71
    uce
    0.70
    âķIJâķIJ
    0.65
    iences
    0.65
    ctuary
    0.65
    rien
    0.64
    Activations Density 0.198%

    No Known Activations