INDEX

Explanations

proper nouns related to geopolitical entities and individuals

oai_token-act-pair · gpt-3.5-turbo

references to major companies or entities involved in financial or corporate dealings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

`.

-0.75

$.

-0.71

"!

-0.71

 ********************************

-0.64

''.

-0.64

 Shutterstock

-0.64

↵Âł

-0.62

tesy

-0.62

.ï¿½

-0.62

:[

-0.62

POSITIVE LOGITS

 dominates

1.01

has

1.00

 hasn

0.91

 retains

0.90

 withdrew

0.85

 opted

0.85

had

0.83

 forbids

0.83

 became

0.83

 expects

0.82

Activations Density 0.923%

proper nouns related to geopolitical entities and individuals

references to major companies or entities involved in financial or corporate dealings

No Comments

No Known Activations