© 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. 5327
    Prev
    Next
    INDEX
    Explanations

    phrases related to choices and access to options

    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
    720
    +0.13
    0.6%
    572
    +0.12
    0.5%
    532
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.13
    0.08
    393
    +0.12
    0.06
    351
    +0.12
    0.05
    Negative Logits
    HAHAHAHA
    -0.69
    GMT
    -0.65
     Gleaming
    -0.63
    geoning
    -0.63
     freezing
    -0.62
     guiActiveUnfocused
    -0.59
     antic
    -0.58
     midnight
    -0.58
    auder
    -0.58
    代
    -0.57
    POSITIVE LOGITS
     others
    1.13
     Others
    0.92
    selves
    0.85
     selves
    0.85
     partners
    0.81
     strangers
    0.80
     yours
    0.78
     Sons
    0.78
     theirs
    0.78
     peers
    0.75
    Activations Density 0.636%

    No Known Activations