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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5315
    Prev
    Next
    INDEX
    Explanations

    terms related to cleaning or washing activities

    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
    113
    +0.12
    0.6%
    420
    +0.10
    0.4%
    361
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.12
    0.02
    249
    +0.10
    0.01
    419
    +0.09
    0.01
    Negative Logits
    */(
    -0.75
    vernment
    -0.71
    ourke
    -0.68
    sson
    -0.65
    acle
    -0.63
    CVE
    -0.62
     Defenders
    -0.61
    eger
    -0.61
    iosity
    -0.60
    IBLE
    -0.60
    POSITIVE LOGITS
     ashore
    1.19
    robe
    1.09
    rooms
    1.01
    room
    0.98
    stakes
    0.96
    cloth
    0.90
    bas
    0.88
    aways
    0.85
    tub
    0.81
    down
    0.80
    Activations Density 0.048%

    No Known Activations