INDEX

Explanations

phrases or sentences containing words related to giving compliments or showing admiration

oai_token-act-pair · gpt-3.5-turbo

instances of the word "praise" and its variations

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

soDeliveryDate

-0.67

abases

-0.66

nery

-0.65

arin

-0.64

pos

-0.63

ridges

-0.62

 Lans

-0.61

space

-0.59

bad

-0.59

pox

-0.58

POSITIVE LOGITS

 praise

1.02

 praises

1.02

ifully

0.89

eous

0.88

hovah

0.84

 praising

0.82

giving

0.80

 acclaim

0.78

iful

0.77

Reviewer

0.71

Activations Density 0.032%

phrases or sentences containing words related to giving compliments or showing admiration

instances of the word "praise" and its variations

No Comments

No Known Activations