INDEX

Explanations

organizations, names, or entities as well as verbs related to decisions or actions

oai_token-act-pair · gpt-3.5-turbo

the verb "has" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

icking

-0.63

ickle

-0.61

eem

-0.59

 Apart

-0.58

 wounding

-0.57

Northern

-0.56

 recalls

-0.55

ear

-0.54

ick

-0.53

ealing

-0.52

POSITIVE LOGITS

 been

1.48

been

1.23

 gotten

1.14

bara

1.11

 begun

1.08

 gone

1.06

 Been

1.03

 undergone

1.03

 become

1.03

 always

0.96

Activations Density 0.485%

organizations, names, or entities as well as verbs related to decisions or actions

the verb "has" in various contexts

No Comments

No Known Activations