INDEX

Explanations

phrases related to professions or expertise

oai_token-act-pair · gpt-3.5-turbo

references to intelligence and achievement 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 @ 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

itant

-0.60

rored

-0.58

avering

-0.52

oval

-0.52

Rated

-0.52

Phase

-0.52

retty

-0.51

ampions

-0.50

Sphere

-0.50

CLASSIFIED

-0.50

POSITIVE LOGITS

to

1.25

to

1.00

To

0.75

nih

0.72

To

0.72

 toget

0.69

TO

0.68

assetsadobe

0.62

for

0.61

 interchange

0.55

Activations Density 1.362%

phrases related to professions or expertise

references to intelligence and achievement in various contexts

No Comments

No Known Activations