INDEX

Explanations

names that end in "ow"

oai_token-act-pair · gpt-3.5-turbo

the word "ow" and its variations or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ually

-0.80

xon

-0.75

 infiltrate

-0.73

 locality

-0.69

ãĥ¼ãĥĨ

-0.69

£ı

-0.67

 Franch

-0.66

 Rouge

-0.61

 siph

-0.61

ĸļ

-0.61

POSITIVE LOGITS

orld

1.28

ards

1.01

een

0.98

restling

0.98

atche

0.97

LAN

0.94

atts

0.94

olves

0.94

aways

0.91

riter

0.90

Activations Density 0.022%

names that end in "ow"

the word "ow" and its variations or occurrences

No Comments

No Known Activations