INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of the name "Da" in various contexts

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

sburgh

-1.15

sburg

-0.82

ãĤ¡

-0.80

eele

-0.73

ï¸ı

-0.72

 guiActiveUnfocused

-0.71

é¾įå¥ĳå£«

-0.70

LESS

-0.70

ments

-0.70

eering

-0.69

POSITIVE LOGITS

emon

1.11

emonic

1.05

isy

1.03

ft

0.97

uman

0.91

uthor

0.86

cha

0.86

iba

0.85

fts

0.85

plin

0.85

Activations Density 0.008%

proper nouns

the repeated mention of the name "Da" in various contexts

No Comments

No Known Activations