INDEX

Explanations

phrases related to the concept of "role in something", often involving different entities or factors and their influence on a specific situation or outcome

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "roles" or "functions" 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 @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

glass

-0.74

itsu

-0.71

ratulations

-0.70

NB

-0.67

Glass

-0.66

ouf

-0.65

sticks

-0.64

alli

-0.63

afe

-0.62

LU

-0.62

POSITIVE LOGITS

 shaping

1.63

 determining

1.52

 facilitating

1.43

 influencing

1.39

 helping

1.30

 promoting

1.28

 ensuring

1.28

 deciding

1.25

 preventing

1.25

 creating

1.24

Activations Density 0.177%

phrases related to the concept of "role in something", often involving different entities or factors and their influence on a specific situation or outcome

references to the concept of "roles" or "functions" in various contexts

No Comments

No Known Activations