INDEX

Explanations

words related to stress, pressure, or urgency

oai_token-act-pair · gpt-3.5-turbo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 triv

-0.75

qus

-0.73

 sole

-0.71

comm

-0.66

 indistinguishable

-0.65

 ideally

-0.65

 sufficient

-0.64

itely

-0.64

ãĥĥãĥī

-0.63

essor

-0.63

POSITIVE LOGITS

 tonight

1.06

 EDITION

0.87

 HERE

0.79

 regarding

0.78

 Join

0.78

!!!

0.78

!!!!

0.77

 OnePlus

0.77

 ASUS

0.76

 Belfast

0.76

Activations Density 0.698%

words related to stress, pressure, or urgency

No Comments

No Known Activations