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

    Neuronpedia

    Jacobian LensNEW
    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. 7150
    Prev
    Next
    INDEX
    Explanations

    the phrase "Along" followed by a number indicating a continuation or addition of information

    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
    240
    +0.12
    0.5%
    721
    +0.10
    0.5%
    422
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    169
    +0.12
    0.02
    355
    +0.10
    0.02
    101
    +0.09
    0.02
    Negative Logits
    EStream
    -0.76
    ļéĨĴ
    -0.60
     dur
    -0.58
    .–
    -0.55
     LINK
    -0.54
    berus
    -0.54
    tein
    -0.54
     amount
    -0.53
    ihad
    -0.53
     EMP
    -0.53
    POSITIVE LOGITS
    come
    1.09
    side
    0.94
    worthy
    0.90
    coming
    0.87
    ho
    0.87
    ward
    0.81
    set
    0.81
    etting
    0.81
    spring
    0.81
    landish
    0.80
    Activations Density 0.101%

    No Known Activations