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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18601
    Prev
    Next
    INDEX
    Explanations

    the abbreviation 'am' followed by a number

    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
    314
    +0.14
    0.6%
    751
    +0.10
    0.5%
    444
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.14
    0.02
    701
    +0.10
    0.02
    444
    +0.09
    0.02
    Negative Logits
     kinderg
    -0.63
     puberty
    -0.63
     steroids
    -0.62
     stakes
    -0.60
     strawberries
    -0.60
    flush
    -0.60
     affairs
    -0.59
     melts
    -0.58
     takeaway
    -0.58
    lift
    -0.58
    POSITIVE LOGITS
    endment
    1.31
    nesty
    1.25
    essage
    1.11
    bitious
    1.10
    ilies
    1.08
    sterdam
    1.08
    azing
    1.06
    munition
    1.05
    otor
    1.04
    icro
    1.03
    Activations Density 0.030%

    No Known Activations