INDEX

Explanations

phrases indicating sources or people familiar with a situation

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

Negative Logits

-0.80

-0.67

Interstitial

-0.65

-0.61

-0.58

 Tooth

-0.57

POSITIVE LOGITS

 briefed

0.88

ahon

0.81

remlin

0.75

axter

0.72

 priv

0.71

 knowledgeable

0.71

tymology

0.69

heastern

0.69

zona

0.67

 familiar

0.67

Activations Density 0.062%

phrases indicating sources or people familiar with a situation

No Known Activations