INDEX

Explanations

verbs related to ensuring or guaranteeing something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "ensure."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

bid

-0.77

NAS

-0.71

court

-0.71

PHOTOS

-0.69

PokÃ©

-0.64

————————

-0.63

ingers

-0.63

 cents

-0.62

CW

-0.62

 Flavoring

-0.62

POSITIVE LOGITS

essential

0.77

rity

0.73

 Ensure

0.72

 ensured

0.72

 compr

0.72

ially

0.71

 safeguards

0.71

 ensures

0.70

 ensure

0.70

reau

0.70

Activations Density 0.020%

verbs related to ensuring or guaranteeing something

occurrences of the word "ensure."

No Comments

No Known Activations