INDEX

Explanations

proper nouns starting with "Re"

oai_token-act-pair · gpt-3.5-turbo

instances of the prefix "Re" as a significant identifier within the text

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

 Pebble

-0.64

 pall

-0.64

 handwriting

-0.63

 trem

-0.62

 Awakens

-0.61

 Chart

-0.59

 Osiris

-0.59

 cove

-0.58

NESS

-0.57

 Pall

-0.57

POSITIVE LOGITS

levant

1.36

uben

1.30

asonable

1.28

ceive

1.19

gex

1.17

usable

1.15

versible

1.14

clamation

1.14

venant

1.12

claim

1.11

Activations Density 0.024%

proper nouns starting with "Re"

instances of the prefix "Re" as a significant identifier within the text

No Comments

No Known Activations