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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 4401
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "for" followed by numerical values or time-related expressions

    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
    314
    +0.16
    0.7%
    373
    +0.12
    0.5%
    10
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    572
    +0.16
    0.06
    362
    +0.12
    0.07
    498
    +0.10
    0.06
    Negative Logits
     correct
    -0.72
     remedy
    -0.69
     exception
    -0.68
     bandwagon
    -0.66
     positives
    -0.66
     exceptions
    -0.65
     google
    -0.64
     omission
    -0.63
     yours
    -0.62
     method
    -0.61
    POSITIVE LOGITS
    ixty
    0.81
    seven
    0.80
    five
    0.80
    irteen
    0.76
    nine
    0.75
    Seven
    0.75
    enced
    0.74
    achu
    0.73
     seven
    0.72
    three
    0.71
    Activations Density 0.361%

    No Known Activations