INDEX

Explanations

acknowledgment or understanding of a statement or situation

oai_token-act-pair · gpt-3.5-turbo

expressions of understanding and acknowledgment in conversations

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

mage

-0.73

tain

-0.66

reet

-0.66

arantine

-0.64

irrel

-0.64

 Ambro

-0.63

rake

-0.62

 mosqu

-0.61

aunder

-0.61

quit

-0.60

POSITIVE LOGITS

 firsthand

0.74

 plenty

0.66

 anecd

0.65

soType

0.64

 myself

0.63

 saddened

0.61

 Cosponsors

0.60

ortium

0.58

 vividly

0.58

 Clause

0.57

Activations Density 0.260%

acknowledgment or understanding of a statement or situation

expressions of understanding and acknowledgment in conversations

No Comments

No Known Activations