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 24576
    5. 8-RES_FS24576-JB
    6. 8312
    Prev
    Next
    INDEX
    Explanations

    places and locations, especially in relation to specific incidents or events

    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
    662
    +0.11
    0.5%
    15
    +0.10
    0.5%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    693
    +0.11
    0.08
    547
    +0.10
    0.06
    224
    +0.09
    0.07
    Negative Logits
    -)
    -0.80
     tho
    -0.60
     tsun
    -0.58
     gra
    -0.57
    =/
    -0.55
    ?)
    -0.55
     gore
    -0.55
    )/
    -0.53
    milo
    -0.52
    )=
    -0.52
    POSITIVE LOGITS
    .
    0.72
    *.
    0.71
     respectively
    0.67
     Wednesday
    0.65
     Thursday
    0.64
     hoping
    0.64
     shortly
    0.62
     Tuesday
    0.62
    .[
    0.62
    \.
    0.59
    Activations Density 0.510%

    No Known Activations