INDEX

Explanations

verbs indicating future actions or intentions

oai_token-act-pair · gpt-3.5-turbo

expressions of intentions or future actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

int

-0.72

weed

-0.70

idge

-0.68

aff

-0.65

asions

-0.65

 Kush

-0.63

asive

-0.63

engu

-0.62

ammy

-0.61

ãĢĲ

-0.61

POSITIVE LOGITS

 Parenthood

1.01

paren

0.84

 accordingly

0.76

 meals

0.71

 Plans

0.70

 pregnancies

0.68

 gestation

0.66

 plans

0.65

 vacations

0.65

 trips

0.65

Activations Density 0.039%

verbs indicating future actions or intentions

expressions of intentions or future actions

No Comments

No Known Activations