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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4197
    Prev
    Next
    INDEX
    Explanations

    references to visits and tourism

    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
    195
    +0.10
    0.5%
    526
    +0.10
    0.4%
    253
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.10
    0.03
    767
    +0.10
    0.02
    253
    +0.09
    0.02
    Negative Logits
    corn
    -0.70
     inherit
    -0.61
    FT
    -0.60
    DX
    -0.58
    SHA
    -0.58
    bra
    -0.57
    Ü
    -0.56
    aft
    -0.56
     CRA
    -0.56
    ILLE
    -0.55
    POSITIVE LOGITS
    acion
    0.87
    shire
    0.76
    itors
    0.76
     abroad
    0.74
    ogly
    0.74
    ULTS
    0.72
     visits
    0.72
    ees
    0.70
    orial
    0.68
     visitation
    0.66
    Activations Density 0.048%

    No Known Activations