INDEX

Explanations

instances of the word "used"

oai_token-act-pair · gpt-3.5-turbo

the phrase "used to" to indicate past habits or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

owship

-0.74

THING

-0.61

atform

-0.57

uta

-0.56

gdala

-0.56

 Ascend

-0.56

redo

-0.54

Gate

-0.53

 Warrant

-0.53

merce

-0.52

POSITIVE LOGITS

to

1.05

fully

1.02

 condoms

0.79

TO

0.73

FUL

0.72

 thereto

0.71

 sparing

0.71

to

0.71

ta

0.66

full

0.64

Activations Density 0.044%

instances of the word "used"

the phrase "used to" to indicate past habits or situations

No Comments

No Known Activations