INDEX

Explanations

verbs related to seeing or perceiving

oai_token-act-pair · gpt-3.5-turbo

instances of the word "see" 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 @ 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

 withd

-0.66

late

-0.60

pour

-0.60

eware

-0.60

nesia

-0.60

 WARN

-0.57

 whistle

-0.57

PHOTOS

-0.56

 Researchers

-0.56

ueless

-0.55

POSITIVE LOGITS

 parallels

1.21

fit

1.02

 similarities

0.90

awed

0.83

 positives

0.82

eye

0.81

 visions

0.80

dust

0.80

 merit

0.79

Ĺ

0.78

Activations Density 0.082%

verbs related to seeing or perceiving

instances of the word "see" and its variations

No Comments

No Known Activations