INDEX

Explanations

verbs that imply a lack of necessity or obligation

oai_token-act-pair · gpt-3.5-turbo

expressions of necessity or lack thereof

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

catentry

-0.80

yrinth

-0.75

uesday

-0.70

utm

-0.67

highest

-0.66

iple

-0.66

slow

-0.64

izzard

-0.64

Pacific

-0.63

worst

-0.63

POSITIVE LOGITS

lessly

1.16

 anymore

1.09

 interruption

0.93

 necessarily

0.83

nor

0.80

rawdownloadcloneembedreportprint

0.75

oppers

0.74

 bothered

0.72

 bother

0.68

ful

0.67

Activations Density 0.033%

verbs that imply a lack of necessity or obligation

expressions of necessity or lack thereof

No Comments

No Known Activations