Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1686
    Prev
    Next
    INDEX
    Explanations

    HTML code snippets

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    679
    +0.10
    0.4%
    496
    +0.09
    0.4%
    315
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.05
    503
    +0.09
    0.03
    586
    +0.09
    0.04
    Negative Logits
    gaard
    -0.72
    issance
    -0.67
    pora
    -0.66
     Stockholm
    -0.65
    ologne
    -0.64
     Kuala
    -0.63
    reditary
    -0.63
     installations
    -0.63
    EVA
    -0.63
     Sabb
    -0.62
    POSITIVE LOGITS
    ></
    1.37
    ><
    1.27
    }}
    1.23
    "></
    1.19
    ">
    1.18
     />
    1.13
    >"
    1.13
    "]=>
    1.12
    }
    1.11
    "]
    1.11
    Activations Density 0.408%

    No Known Activations