INDEX

Explanations

phrases related to confrontation or conflict

oai_token-act-pair · gpt-3.5-turbo

strong opinions or reactions about superhero movies and related cultural commentary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

hari

-0.70

(>

-0.69

 UNCLASSIFIED

-0.67

'[

-0.66

ItemImage

-0.66

 Palest

-0.66

ascript

-0.64

[+

-0.64

XY

-0.63

Therefore

-0.63

POSITIVE LOGITS

 surprises

0.80

 eyebrows

0.68

PHOTOS

0.68

 downright

0.63

 headlines

0.62

 alarms

0.61

 Clown

0.61

ueller

0.61

 selfie

0.61

 laughs

0.61

Activations Density 1.204%

phrases related to confrontation or conflict

strong opinions or reactions about superhero movies and related cultural commentary

No Comments

No Known Activations