© 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. 5753
    Prev
    Next
    INDEX
    Explanations

    references to locations or objects that are described as being "nearby."

    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
    471
    +0.09
    0.4%
    36
    +0.09
    0.4%
    580
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.09
    0.02
    471
    +0.09
    0.01
    469
    +0.09
    0.01
    Negative Logits
    anwhile
    -0.85
    ctx
    -0.80
    ppe
    -0.78
    inelli
    -0.74
    _-
    -0.74
    alion
    -0.73
    RANT
    -0.72
    icer
    -0.72
    apego
    -0.72
    urer
    -0.72
    POSITIVE LOGITS
     suburbs
    0.81
     buildings
    0.81
     Territories
    0.80
     businesses
    0.80
     neighbors
    0.79
     villages
    0.78
     towns
    0.78
     islands
    0.77
     neighbor
    0.76
     neighbour
    0.76
    Activations Density 0.053%

    No Known Activations