© 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 12288
    9. 8-RES_FS12288-JB
    11. 314
    Prev
    Next
    INDEX
    Explanations

    information related to legal and political discussions around controlled substances such as marijuana and other drugs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    373
    +0.11
    0.5%
    680
    +0.10
    0.5%
    321
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.11
    0.05
    117
    +0.10
    0.06
    264
    +0.09
    0.03
    Negative Logits
    %.
    -0.79
    .<
    -0.77
    .:
    -0.76
    "!
    -0.76
    !".
    -0.72
    .(
    -0.72
    ."
    -0.70
    ".
    -0.69
    .",
    -0.68
    !!!!!
    -0.67
    POSITIVE LOGITS
    *)
    1.07
    )}
    0.98
    })
    0.96
     )]
    0.94
    ?)
    0.93
    )\
    0.92
     ?)
    0.91
    )]
    0.89
    -)
    0.89
    +)
    0.88
    Activations Density 2.559%

    No Known Activations