INDEX

Explanations

mentions of requiring permission, approval or consent in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to permission and approval processes

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

famous

-0.74

ãĥł

-0.73

anish

-0.67

empl

-0.67

character

-0.66

verage

-0.65

 pioneered

-0.65

together

-0.65

aunder

-0.63

 nutshell

-0.63

POSITIVE LOGITS

 superiors

1.28

 Almighty

0.98

 Heaven

0.92

 STATS

0.90

 supervisors

0.89

 competent

0.87

 authorities

0.85

 shareholders

0.84

 Congress

0.84

 Parliament

0.84

Activations Density 0.280%

mentions of requiring permission, approval or consent in various contexts

references to permission and approval processes

No Comments

No Known Activations