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. 4201
    Prev
    Next
    INDEX
    Explanations

    phrases related to hosting or presenting events or shows

    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
    467
    +0.10
    0.5%
    584
    +0.10
    0.4%
    25
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    584
    +0.10
    0.03
    146
    +0.10
    0.02
    711
    +0.09
    0.01
    Negative Logits
    Ĥİ
    -0.90
    osate
    -0.70
    obil
    -0.66
     disillusion
    -0.66
    ahon
    -0.66
     omission
    -0.65
    issance
    -0.64
    ãĤ´
    -0.64
    é¾įå
    -0.64
    Subject
    -0.64
    POSITIVE LOGITS
     Cosponsors
    0.73
     guests
    0.70
    poke
    0.69
    riott
    0.68
    esses
    0.68
    night
    0.68
     Guests
    0.67
    mit
    0.67
     Avatar
    0.66
    rival
    0.66
    Activations Density 0.584%

    No Known Activations