© 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. 4661
    Prev
    Next
    INDEX
    Explanations

    references to edits or modifications to 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
    373
    +0.23
    1.1%
    551
    +0.11
    0.5%
    241
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.23
    0.06
    702
    +0.11
    0.05
    165
    +0.10
    0.04
    Negative Logits
    ivable
    -0.79
    milo
    -0.69
    ciating
    -0.66
    wagen
    -0.64
    etsk
    -0.63
    cel
    -0.61
    aspers
    -0.61
    bage
    -0.61
    ensitive
    -0.61
     SIG
    -0.59
    POSITIVE LOGITS
     edit
    0.74
    Merit
    0.63
    Spoiler
    0.63
    Mah
    0.62
     Appears
    0.62
    VERTISEMENT
    0.61
    Param
    0.61
    Legendary
    0.61
    Ep
    0.60
    IJ
    0.59
    Activations Density 0.069%

    No Known Activations