INDEX

Explanations

locations and descriptive details within a narrative

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

specific geographical locations and landmarks

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

phas

-0.76

ially

-0.67

 advisers

-0.63

 sidel

-0.58

 repetition

-0.58

 benign

-0.57

 quotas

-0.57

 acknowled

-0.56

inarily

-0.56

respond

-0.55

POSITIVE LOGITS

!!!!

1.08

!!!

1.01

 ðŁĺ

1.01

!!

1.01

!!

1.00

?!

0.95

 Airport

0.95

:)

0.94

!!!!!

0.94

!!!!!!!!

0.93

Activations Density 0.383%

locations and descriptive details within a narrative

specific geographical locations and landmarks

No Comments

No Known Activations