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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 41442
    Prev
    Next
    INDEX
    Explanations

    statistics related to public opinion and demographic information

    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
    745
    +0.11
    0.5%
    648
    +0.10
    0.5%
    288
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.11
    0.03
    15
    +0.10
    0.03
    455
    +0.10
    0.03
    Negative Logits
    inventoryQuantity
    -0.78
     extraord
    -0.70
    kefeller
    -0.69
    ãĤ´ãĥ³
    -0.68
    tnc
    -0.64
     Mercenary
    -0.63
     Corpus
    -0.63
    ILA
    -0.62
     Samp
    -0.62
     interchange
    -0.62
    POSITIVE LOGITS
     polled
    1.36
     surveyed
    1.22
     disapprove
    1.10
     voted
    0.98
     subscribed
    0.93
     perceive
    0.87
     oppose
    0.86
     approve
    0.83
     tuned
    0.83
     prefer
    0.83
    Activations Density 0.075%

    No Known Activations