INDEX

Explanations

opinions or thoughts expressed by individuals

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĤ´ãĥ³

-1.02

.<

-0.89

.*

-0.89

.(

-0.88

!.

-0.85

ãĢĤ

-0.81

.).

-0.81

.</

-0.80

%.

-0.77

.#

-0.77

POSITIVE LOGITS

1.52

,"

1.26

['

1.15

,'"

1.12

),"

1.10

,''

0.99

 âĢ¦

0.91

.,"

0.90

%"

0.89

,'

0.86

Activations Density 1.248%

opinions or thoughts expressed by individuals

No Comments

No Known Activations