INDEX

Explanations

features related to eating or food consumption

oai_token-act-pair · gpt-3.5-turbo

references to the act of eating

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 easing

-0.73

 Strat

-0.67

VK

-0.63

 feasibility

-0.62

 traff

-0.61

 bidding

-0.61

 initiating

-0.61

 operating

-0.61

VERSION

-0.61

 cubic

-0.60

POSITIVE LOGITS

hered

1.17

eat

0.99

ibles

0.90

neau

0.89

eteria

0.88

Eat

0.87

terson

0.86

rice

0.86

hers

0.86

worms

0.85

Activations Density 0.007%

features related to eating or food consumption

references to the act of eating

No Comments

No Known Activations