© 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. 11917
    Prev
    Next
    INDEX
    Explanations

    descriptions related to journeys or travels, including specifics like locations and events along the way

    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
    481
    +0.23
    1.1%
    447
    +0.19
    0.9%
    373
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    582
    +0.23
    0.04
    14
    +0.19
    0.03
    598
    +0.12
    0.02
    Negative Logits
    Firstly
    -0.78
     pc
    -0.72
    Latest
    -0.71
     ðŁĺ
    -0.71
    ĵĺ
    -0.71
     cpu
    -0.69
    Vote
    -0.69
    Byte
    -0.69
     ;)
    -0.69
    goo
    -0.68
    POSITIVE LOGITS
     postwar
    0.82
     novelist
    0.80
     poet
    0.80
     adolescence
    0.79
     autobi
    0.79
     historian
    0.78
     solitude
    0.78
    toggle
    0.77
     vividly
    0.76
     1953
    0.76
    Activations Density 0.874%

    No Known Activations