INDEX

Explanations

mentions of hunger and related concepts

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

-0.81

channelAvailability

-0.77

semble

-0.77

struct

-0.74

minus

-0.72

manship

-0.70

knit

-0.68

agall

-0.67

 abbrevi

-0.67

edu

-0.66

POSITIVE LOGITS

 appetite

1.03

 hungry

1.02

 thirsty

0.92

 craving

0.90

 appet

0.88

 hunger

0.85

 thirst

0.84

 meals

0.84

 Hungry

0.80

 eater

0.79

Activations Density 0.027%

mentions of hunger and related concepts

No Comments

No Known Activations