INDEX

Explanations

self-introductions and biographical information

oai_token-act-pair · gpt-3.5-turbo Triggered 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

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 deterrent

-0.86

 undercut

-0.78

 harms

-0.76

ilitarian

-0.75

 harsher

-0.74

 undermines

-0.74

forcement

-0.73

 curtail

-0.73

 excess

-0.72

 undermined

-0.72

POSITIVE LOGITS

Hi

0.97

Hello

0.94

 Hello

0.86

 Joined

0.85

 hello

0.83

Welcome

0.82

 Anon

0.82

 Located

0.77

 alias

0.77

 reside

0.74

Activations Density 0.451%

self-introductions and biographical information

No Comments

No Known Activations