INDEX

Explanations

negative statements or challenges about assumptions

oai_token-act-pair · gpt-3.5-turbo

negative contractions indicating denial or negation

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

cius

-0.70

isively

-0.70

farious

-0.64

wards

-0.62

pick

-0.62

ledge

-0.62

plates

-0.62

ways

-0.60

izen

-0.59

moil

-0.59

POSITIVE LOGITS

ĥ

0.73

Ĥ

0.71

OTAL

0.69

GD

0.69

 Mahjong

0.69

SPONSORED

0.68

rame

0.67

IELD

0.67

 Bungie

0.65

soType

0.64

Activations Density 0.208%

negative statements or challenges about assumptions

negative contractions indicating denial or negation

No Comments

No Known Activations