© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 45518
    Prev
    Next
    INDEX
    Explanations

    the presence of entities (like people or organizations) and their relationships within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    258
    +0.11
    0.5%
    574
    +0.11
    0.5%
    71
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.11
    0.03
    463
    +0.11
    0.03
    299
    +0.10
    0.03
    Negative Logits
    acity
    -0.63
    oshenko
    -0.62
    oops
    -0.60
     Hover
    -0.60
    ayson
    -0.59
    instead
    -0.58
    ANE
    -0.58
     instead
    -0.57
     srfAttach
    -0.57
    ouf
    -0.56
    POSITIVE LOGITS
     surveyed
    1.19
     imaginable
    0.98
     polled
    0.92
     interviewed
    0.88
     reviewed
    0.85
     studied
    0.83
     sampled
    0.83
     examined
    0.82
    soever
    0.81
     tested
    0.78
    Activations Density 0.182%

    No Known Activations