INDEX

Explanations

proper nouns related to companies, organizations, and people

oai_token-act-pair · gpt-3.5-turbo

references to companies and organizations in the context of news and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 thereto

-0.62

":{"

-0.62

pires

-0.61

 ILCS

-0.58

eded

-0.57

leted

-0.57

etc

-0.54

arest

-0.53

ranged

-0.53

"!

-0.52

POSITIVE LOGITS

 yesterday

1.42

 shortly

1.39

 earlier

1.30

 last

1.22

 Tuesday

1.11

 Wednesday

1.11

 Thursday

1.07

 Monday

1.06

 after

1.04

 during

1.01

Activations Density 0.900%

proper nouns related to companies, organizations, and people

references to companies and organizations in the context of news and events

No Comments

No Known Activations