INDEX

Explanations

phrases related to the concept of time and effort

oai_token-act-pair · gpt-3.5-turbo

the phrase "to" used in various contexts indicating intention or purpose

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

soDeliveryDate

-0.90

cens

-0.82

listed

-0.72

 Observer

-0.69

furt

-0.66

need

-0.66

hent

-0.64

croft

-0.62

ively

-0.61

hops

-0.59

POSITIVE LOGITS

 accommodate

1.10

 ensure

1.03

 accomplish

1.00

 promote

0.97

 resolve

0.97

 minimize

0.96

 achieve

0.96

 conserve

0.95

 fulfill

0.94

 improve

0.93

Activations Density 0.357%

phrases related to the concept of time and effort

the phrase "to" used in various contexts indicating intention or purpose

No Comments

No Known Activations