INDEX

Explanations

instances where the word "may" is used in context

oai_token-act-pair · gpt-3.5-turbo

conditional statements or possibilities expressed through the word "may."

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

 Enforcement

-0.67

feeding

-0.66

icial

-0.65

raphic

-0.65

ciating

-0.64

cies

-0.62

ging

-0.62

 Dragonbound

-0.61

performing

-0.60

zeb

-0.60

POSITIVE LOGITS

bes

0.94

onna

0.94

hap

0.93

 incent

0.82

haps

0.78

nard

0.74

 misunder

0.73

NF

0.72

 conclud

0.72

ynski

0.71

Activations Density 0.084%

instances where the word "may" is used in context

conditional statements or possibilities expressed through the word "may."

No Comments

No Known Activations