INDEX

Explanations

verbs indicating action or intention

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate necessity, capability, or ongoing actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

bury

-0.64

KL

-0.56

hack

-0.54

Sly

-0.52

 Britain

-0.52

 paternity

-0.51

 Pigs

-0.50

 Truth

-0.50

 Seah

-0.49

hin

-0.49

POSITIVE LOGITS

ãĥĩãĤ£

0.65

âĵĺ

0.65

ãĥĦ

0.64

pmwiki

0.64

Tokens

0.63

 nevertheless

0.61

 nonetheless

0.59

 partName

0.59

 sugg

0.58

 downright

0.58

Activations Density 0.986%

verbs indicating action or intention

phrases that indicate necessity, capability, or ongoing actions

No Comments

No Known Activations