INDEX

Explanations

phrases related to starting or taking action on something

oai_token-act-pair · gpt-3.5-turbo

prepositions and their associations with actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

LY

-0.65

 Liang

-0.63

theless

-0.60

Begin

-0.58

 Lang

-0.58

chief

-0.58

 omission

-0.58

]}

-0.57

Berry

-0.57

 Bulg

-0.57

POSITIVE LOGITS

issions

0.75

retty

0.75

utters

0.75

ez

0.74

anan

0.73

entary

0.73

/+

0.73

itary

0.72

 traction

0.70

izont

0.70

Activations Density 0.090%

phrases related to starting or taking action on something

prepositions and their associations with actions or states

No Comments

No Known Activations