INDEX

Explanations

phrases containing scientific or technical terms

oai_token-act-pair · gpt-3.5-turbo

sentences that present a definitive or conclusive statement

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

 estate

-0.79

 dime

-0.78

 closet

-0.76

ibur

-0.76

 reven

-0.74

tyr

-0.73

 silent

-0.73

 altar

-0.72

 tier

-0.72

 hating

-0.71

POSITIVE LOGITS

 Researchers

1.37

 Scientists

1.24

 Moreover

1.14

Researchers

1.13

 Furthermore

1.12

 PLoS

1.04

 Studies

1.04

Scientists

1.03

 Therefore

1.03

 Additionally

1.02

Activations Density 0.421%

phrases containing scientific or technical terms

sentences that present a definitive or conclusive statement

No Comments

No Known Activations