© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19851
    Prev
    Next
    INDEX
    Explanations

    words related to expectations and comparisons within a context of personal development and investment

    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
    7
    +0.12
    0.5%
    253
    +0.10
    0.5%
    512
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.12
    0.05
    102
    +0.10
    0.06
    718
    +0.10
    0.06
    Negative Logits
    afia
    -0.88
    acas
    -0.78
    essor
    -0.75
    anamo
    -0.72
    ricanes
    -0.71
    itches
    -0.71
    glers
    -0.70
    aido
    -0.70
    Shape
    -0.69
    enaries
    -0.68
    POSITIVE LOGITS
     achievable
    1.18
     punishable
    1.18
     advisable
    1.13
     unavoidable
    1.10
     counterproductive
    1.09
     inevitable
    1.07
     indicative
    1.06
     consequential
    1.03
     detrimental
    1.02
     feasible
    0.99
    Activations Density 0.457%

    No Known Activations