INDEX

Explanations

mentions of weights or measurements in pounds

oai_token-act-pair · gpt-3.5-turbo

references to weight and measurements in pounds and kilograms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

istically

-0.80

cknow

-0.78

opol

-0.77

choes

-0.73

vironment

-0.73

 externalToEVAOnly

-0.71

 Nare

-0.70

inav

-0.69

 Emin

-0.67

ovie

-0.66

POSITIVE LOGITS

 sterling

1.23

cake

1.00

 gorilla

0.98

 pounds

0.97

lbs

0.96

 heavier

0.93

lbs

0.93

 overweight

0.89

 weight

0.87

cakes

0.84

Activations Density 0.027%

mentions of weights or measurements in pounds

references to weight and measurements in pounds and kilograms

No Comments

No Known Activations