INDEX

Explanations

words related to locations and medical assistance

oai_token-act-pair · gpt-3.5-turbo

references to specific geographic locations and entities related to them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

zsche

-0.80

abytes

-0.74

AUD

-0.73

jri

-0.65

natureconservancy

-0.63

FACE

-0.62

oslav

-0.61

culosis

-0.60

llo

-0.60

olls

-0.60

POSITIVE LOGITS

ãĥ¼ãĥĨ

0.93

ä½ľ

0.73

 Verge

0.67

ãĥ¼ãĥĨãĤ£

0.66

 Creed

0.66

Allah

0.64

BILITIES

0.64

advertisement

0.64

ãĥĢ

0.62

ffect

0.62

Activations Density 0.391%

words related to locations and medical assistance

references to specific geographic locations and entities related to them

No Comments

No Known Activations