© 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. 20051
    Prev
    Next
    INDEX
    Explanations

    terms related to politics and government scandals

    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
    +0.13
    0.6%
    221
    +0.10
    0.5%
    489
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.13
    0.05
    460
    +0.10
    0.05
    762
    +0.10
    0.07
    Negative Logits
    "))
    -0.65
    "],
    -0.64
    ]),
    -0.63
    ]).
    -0.63
    "),
    -0.60
     acknow
    -0.58
    estern
    -0.57
    "},
    -0.56
    ]);
    -0.55
    Haunted
    -0.55
    POSITIVE LOGITS
    ,
    0.84
    ,.
    0.78
    *,
    0.75
    .,
    0.71
    _.
    0.66
    ,,
    0.64
    .*
    0.61
    !,
    0.61
    âĢķ
    0.60
    *.
    0.59
    Activations Density 0.616%

    No Known Activations