© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 18944
    Prev
    Next
    INDEX
    Explanations

    phrases related to loyalty or public representation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    480
    +0.20
    0.9%
    87
    +0.13
    0.6%
    464
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.20
    0.06
    42
    +0.13
    0.05
    345
    +0.11
    0.05
    Negative Logits
    forth
    -0.82
    ppard
    -0.72
    stood
    -0.67
    alore
    -0.66
     spont
    -0.64
     Borders
    -0.64
     Genie
    -0.62
     Overse
    -0.61
    AFTA
    -0.60
     Stain
    -0.60
    POSITIVE LOGITS
    actionDate
    0.88
     ][
    0.87
     ]
    0.83
     TEXT
    0.77
    "]=>
    0.77
     ];
    0.75
     guiActive
    0.72
     guiActiveUnfocused
    0.71
     ><
    0.71
     async
    0.71
    Activations Density 0.151%

    No Known Activations