© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5877
    Prev
    Next
    INDEX
    Explanations

    repetitions of the phrase "come back"

    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
    69
    +0.13
    0.6%
    373
    +0.11
    0.5%
    677
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    677
    +0.13
    0.03
    351
    +0.11
    0.02
    104
    +0.10
    0.02
    Negative Logits
    stood
    -0.67
    conn
    -0.66
    ghai
    -0.61
     Whedon
    -0.61
    SourceFile
    -0.61
     PID
    -0.60
    iop
    -0.59
    ciples
    -0.58
     Nebula
    -0.58
     Cosmos
    -0.58
    POSITIVE LOGITS
     alive
    0.79
     refreshed
    0.68
     stronger
    0.67
    ARCH
    0.65
     undone
    0.65
     hither
    0.65
     ashore
    0.64
     handy
    0.63
    eper
    0.63
    antic
    0.63
    Activations Density 0.040%

    No Known Activations