INDEX

Explanations

quotes, attributions, and statements

oai_token-act-pair · gpt-3.5-turbo

instances of the word "was" indicating significant statements or descriptions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

!'

-0.66

Â·Â·

-0.64

!'"

-0.62

?'

-0.59

ress

-0.58

 Battles

-0.58

?'"

-0.58

 Quarter

-0.57

.'

-0.56

 Vers

-0.56

POSITIVE LOGITS

 "...

1.07

1.03

 "âĢ¦

1.01

"[

0.96

"'

0.87

''

0.87

 unlikely

0.87

"#

0.85

 indeed

0.84

 akin

0.82

Activations Density 0.423%

quotes, attributions, and statements

instances of the word "was" indicating significant statements or descriptions

No Comments

No Known Activations