© 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 49152
    9. 8-RES_FS49152-JB
    11. 26727
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations and related events

    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
    480
    +0.48
    2.5%
    585
    +0.10
    0.5%
    347
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.48
    0.00
    288
    +0.10
    0.07
    752
    +0.09
    0.06
    Negative Logits
    Ħ¢
    -0.74
     });
    -0.71
    )?
    -0.69
    ?).
    -0.68
     persists
    -0.67
    .''.
    -0.62
     }}
    -0.62
    }}}
    -0.59
    etheless
    -0.58
    %).
    -0.58
    POSITIVE LOGITS
    wagon
    0.64
    env
    0.62
     wilderness
    0.58
    orgetown
    0.58
     Correctional
    0.56
     fray
    0.54
     Sussex
    0.53
     hospital
    0.52
     Wilderness
    0.52
     Prison
    0.52
    Activations Density 0.584%

    No Known Activations