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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 45915
    Prev
    Next
    INDEX
    Explanations

    variations of the word "memory" in different contexts

    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
    389
    +0.11
    0.5%
    464
    +0.10
    0.5%
    619
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    619
    +0.11
    0.01
    464
    +0.10
    0.01
    334
    +0.10
    0.01
    Negative Logits
     ASC
    -0.76
     Aval
    -0.72
     Highlander
    -0.72
     Ducks
    -0.65
    DERR
    -0.65
    RAFT
    -0.64
     Elves
    -0.64
     Palmer
    -0.63
     diver
    -0.62
     accelerating
    -0.62
    POSITIVE LOGITS
    phis
    1.36
    oir
    1.33
    bered
    1.21
    orial
    1.16
    oire
    1.16
    abilia
    1.15
    eor
    1.15
    orable
    1.13
    etic
    1.12
    etics
    1.12
    Activations Density 0.003%

    No Known Activations