INDEX

Explanations

pronouns followed by the verb "say" or "regard"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ancial

-0.59

 Screw

-0.57

ammy

-0.57

 surprises

-0.56

 refresh

-0.56

 concentration

-0.56

hang

-0.55

 Supply

-0.55

YES

-0.55

 compatibility

-0.54

POSITIVE LOGITS

 termed

1.49

 dubbed

1.16

 euphem

1.10

 deems

1.10

called

1.09

dub

1.09

 called

1.08

 deem

1.06

 deemed

1.03

 perceive

1.00

Activations Density 0.121%

pronouns followed by the verb "say" or "regard"

No Comments

No Known Activations