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

    Neuronpedia

    Jacobian LensNEW
    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. 7700
    Prev
    Next
    INDEX
    Explanations

    text related to network setup and technology

    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
    581
    +0.16
    0.7%
    88
    +0.12
    0.5%
    476
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    206
    +0.16
    0.03
    581
    +0.12
    0.03
    654
    +0.10
    0.03
    Negative Logits
    rers
    -0.70
    rer
    -0.66
    tle
    -0.65
    sem
    -0.65
    ror
    -0.65
    interstitial
    -0.64
    ahime
    -0.63
    soDeliveryDate
    -0.63
    ricanes
    -0.63
    oother
    -0.62
    POSITIVE LOGITS
     imaginable
    1.05
    pires
    0.94
     existence
    0.87
     except
    0.86
    except
    0.81
     sight
    0.80
    soever
    0.80
     planet
    0.75
     totality
    0.74
     globe
    0.73
    Activations Density 0.191%

    No Known Activations