INDEX

Explanations

phrases related to watching activities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "watch" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

esan

-0.85

ãĥ´

-0.77

enture

-0.72

ItemTracker

-0.71

afort

-0.71

Enlarge

-0.69

hesion

-0.67

 suscept

-0.67

quart

-0.67

interstitial

-0.66

POSITIVE LOGITS

tv

1.13

TV

1.12

 television

1.11

dogs

1.08

 videos

1.08

 movies

1.05

 documentaries

1.01

 helpless

1.01

dog

0.98

 films

0.96

Activations Density 0.056%

phrases related to watching activities

instances of the word "watch" and its variations

No Comments

No Known Activations