INDEX

Explanations

mentions of food and dietary habits, specifically focusing on whole foods

oai_token-act-pair · gpt-3.5-turbo

terms related to whole foods and health

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anwhile

-0.69

cing

-0.64

CU

-0.63

ANS

-0.62

 Predators

-0.62

abilities

-0.58

IDS

-0.58

onson

-0.58

KER

-0.57

Fight

-0.57

POSITIVE LOGITS

heartedly

1.71

hearted

1.41

meal

1.09

 genome

0.79

hog

0.77

 Foods

0.72

gam

0.70

 wheat

0.70

 genomes

0.68

orse

0.67

Activations Density 0.030%

mentions of food and dietary habits, specifically focusing on whole foods

terms related to whole foods and health

No Comments

No Known Activations