INDEX

Explanations

words related to impairment or impaired conditions

oai_token-act-pair · gpt-3.5-turbo

terms related to impairment and its effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

soDeliveryDate

-0.76

MET

-0.73

 Aval

-0.73

ICAN

-0.72

Tik

-0.68

çĭ

-0.65

é¾įåĸļå£«

-0.65

Ð´

-0.65

atorial

-0.63

TING

-0.63

POSITIVE LOGITS

 impaired

1.42

 impair

1.16

 impairment

1.15

 adversely

0.85

 cripp

0.81

 retard

0.80

 inhib

0.77

 exerc

0.76

 hemor

0.75

 epile

0.74

Activations Density 0.013%

words related to impairment or impaired conditions

terms related to impairment and its effects

No Comments

No Known Activations