INDEX

Explanations

words related to archeological discoveries and historical artifacts

oai_token-act-pair · gpt-3.5-turbo

words or concepts related to obstruction or barriers

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

£ı

-0.68

bourg

-0.65

Marie

-0.64

hyde

-0.62

warm

-0.62

ĸļ

-0.62

zig

-0.61

xus

-0.61

 Bombay

-0.60

pring

-0.60

POSITIVE LOGITS

uary

0.87

itely

0.83

Wan

0.79

atch

0.73

acles

0.73

Pai

0.67

ocument

0.66

ormon

0.66

Synopsis

0.65

acl

0.64

Activations Density 0.095%

words related to archeological discoveries and historical artifacts

words or concepts related to obstruction or barriers

No Comments

No Known Activations