INDEX

Explanations

passages containing the word "directly."

oai_token-act-pair · gpt-3.5-turbo

terms that indicate direct relationships or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

gerald

-0.83

Cla

-0.70

ifully

-0.69

 thoroughly

-0.69

ittal

-0.69

 cautiously

-0.68

Daily

-0.67

 meticulously

-0.63

 Scor

-0.62

Thumbnail

-0.62

POSITIVE LOGITS

 contradicted

1.00

 contradict

0.88

ebted

0.87

 contradicts

0.86

 impacted

0.83

 attributable

0.82

forward

0.82

 impacting

0.80

ect

0.75

linked

0.74

Activations Density 0.029%

passages containing the word "directly."

terms that indicate direct relationships or connections

No Comments

No Known Activations