INDEX

Explanations

proper nouns related to a specific place or event

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "id"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

bilt

-0.87

andise

-0.75

izabeth

-0.74

 Seym

-0.72

 silence

-0.70

ndum

-0.65

=-=-

-0.64

estern

-0.63

Nun

-0.62

 biscuits

-0.60

POSITIVE LOGITS

irection

1.23

ividual

1.13

iots

1.01

iosyncr

0.99

eways

0.98

gets

0.98

olon

0.97

imensional

0.97

ocument

0.92

der

0.91

Activations Density 0.064%

proper nouns related to a specific place or event

occurrences of the word "id"

No Comments

No Known Activations