INDEX

Explanations

words related to feeling fed up or frustrated with a situation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "fed" indicating the feeding or provision of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.74

isms

-0.73

 Ashes

-0.62

istic

-0.60

ities

-0.58

Goo

-0.58

 Device

-0.57

 Difference

-0.57

 Quarterly

-0.57

 Templar

-0.56

POSITIVE LOGITS

oras

1.28

ora

1.23

Fed

0.95

rique

0.94

ric

0.91

elsen

0.88

rix

0.86

fed

0.85

¡

0.84

ression

0.84

Activations Density 0.007%

words related to feeling fed up or frustrated with a situation

instances of the word "fed" indicating the feeding or provision of something

No Comments

No Known Activations