INDEX

Explanations

phrases indicating an action or directive

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "To" 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 @ 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

 nets

-0.73

hops

-0.66

 drops

-0.64

pins

-0.63

soDeliveryDate

-0.63

 dips

-0.61

 wipes

-0.61

itates

-0.61

 taps

-0.60

 diapers

-0.60

POSITIVE LOGITS

ilet

1.23

 summarize

1.01

oru

0.95

ffee

0.95

 reiterate

0.94

asty

0.92

pping

0.90

 clarify

0.89

othy

0.87

ppings

0.86

Activations Density 0.067%

phrases indicating an action or directive

occurrences of the word "To" in various contexts

No Comments

No Known Activations