INDEX

Explanations

phrases related to manufacturing or production

oai_token-act-pair · gpt-3.5-turbo

instances of the word "produce" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

laus

-0.82

imb

-0.73

enhagen

-0.71

stra

-0.70

hattan

-0.70

uyomi

-0.68

ede

-0.67

uni

-0.67

pan

-0.64

mares

-0.63

POSITIVE LOGITS

ivity

0.86

encers

0.80

 offspring

0.79

å¥³

0.73

rious

0.72

ivities

0.71

 prod

0.69

nces

0.67

Output

0.67

 outputs

0.65

Activations Density 0.045%

phrases related to manufacturing or production

instances of the word "produce" and its variations

No Comments

No Known Activations