INDEX

Explanations

references to large or influential entities, such as corporations or organizations

oai_token-act-pair · gpt-3.5-turbo

references to significant companies or businesses identified as "giants."

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

iggins

-0.80

leigh

-0.74

ãĤ¯

-0.73

bian

-0.72

croft

-0.72

odox

-0.72

range

-0.70

pmwiki

-0.70

othy

-0.70

veyard

-0.68

POSITIVE LOGITS

 headquartered

1.11

 subsidiaries

0.93

 corporation

0.92

 executives

0.88

 jointly

0.86

 subsidiary

0.85

 Anthem

0.84

 titan

0.78

 advertis

0.78

 retailer

0.77

Activations Density 0.171%

references to large or influential entities, such as corporations or organizations

references to significant companies or businesses identified as "giants."

No Comments

No Known Activations