INDEX

Explanations

restaurant-related phrases and items

oai_token-act-pair · gpt-3.5-turbo

titles or names of places and establishments

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

$.

-0.92

`.

-0.89

}.

-0.83

>.

-0.80

rather

-0.75

thia

-0.73

adequ

-0.72

yond

-0.71

=]

-0.70

().

-0.70

POSITIVE LOGITS

 consists

1.01

 comprises

0.98

has

0.91

 represents

0.91

 consisted

0.90

 operates

0.88

is

0.87

 includes

0.86

 appears

0.85

 version

0.85

Activations Density 0.810%

restaurant-related phrases and items

titles or names of places and establishments

No Comments

No Known Activations