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. 2105
    Prev
    Next
    INDEX
    Explanations

    sentences related to accepting oneself and others despite external judgment

    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
    358
    +0.13
    0.6%
    658
    +0.10
    0.4%
    102
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.13
    0.13
    70
    +0.10
    0.12
    750
    +0.09
    0.07
    Negative Logits
    raltar
    -0.76
    è¦ļéĨĴ
    -0.74
    xtap
    -0.61
    ?????-?????-
    -0.60
     encount
    -0.60
    è£ħ
    -0.59
    ccording
    -0.59
    rontal
    -0.59
    icipated
    -0.58
     earthqu
    -0.57
    POSITIVE LOGITS
     theirs
    1.46
     him
    1.11
     hers
    1.08
     us
    0.89
     themselves
    0.89
     me
    0.88
     yours
    0.87
    their
    0.87
     them
    0.86
     their
    0.85
    Activations Density 2.966%

    No Known Activations