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. 45568
    Prev
    Next
    INDEX
    Explanations

    words related to finance and economic data

    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
    756
    +0.12
    0.6%
    7
    +0.10
    0.5%
    579
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.12
    0.03
    284
    +0.10
    0.02
    588
    +0.10
    0.02
    Negative Logits
    ĪĴ
    -0.62
    çĽ
    -0.60
     Houth
    -0.60
    Austral
    -0.59
    Brow
    -0.59
    WOR
    -0.58
     propensity
    -0.58
     Grateful
    -0.58
     CPS
    -0.57
    Fourth
    -0.57
    POSITIVE LOGITS
    ourt
    1.19
    zyk
    1.03
    ookie
    1.00
    chio
    0.98
    olor
    0.96
    amera
    0.96
    ourse
    0.91
    urrency
    0.89
    ussions
    0.88
    reek
    0.88
    Activations Density 0.023%

    No Known Activations