INDEX

Explanations

phrases indicating a complete denial or negation of something

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a lack of beneficial impact or relationship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 proverb

-0.71

 Knot

-0.69

 Debor

-0.67

erva

-0.65

olk

-0.64

 Paragu

-0.64

KGB

-0.63

emetery

-0.62

oute

-0.61

ŃĶ

-0.61

POSITIVE LOGITS

 whatsoever

1.22

 imaginable

0.87

soever

0.77

 resembling

0.75

eter

0.74

 resembles

0.74

caster

0.73

isal

0.71

 construed

0.70

 involved

0.70

Activations Density 0.041%

phrases indicating a complete denial or negation of something

phrases that indicate a lack of beneficial impact or relationship

No Comments

No Known Activations