INDEX

Explanations

phrases related to removal or elimination

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the removal of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hof

-0.73

SPONSORED

-0.69

 ACTIONS

-0.67

Business

-0.63

 Bout

-0.63

icion

-0.62

Ready

-0.61

eworks

-0.61

 Prices

-0.61

Demand

-0.61

POSITIVE LOGITS

 veil

1.03

 altogether

0.98

 traces

0.91

 barrier

0.90

 unwanted

0.88

 offending

0.87

 restraints

0.86

 barriers

0.85

 entirely

0.84

 inhib

0.83

Activations Density 0.214%

phrases related to removal or elimination

phrases that indicate the removal of something

No Comments

No Known Activations