INDEX

Explanations

verbs related to movement or change of position

oai_token-act-pair · gpt-3.5-turbo

verbs indicating an action or participation in an event

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

rone

-0.80

zo

-0.67

âĹ¼

-0.64

 Koreans

-0.64

ria

-0.63

ricular

-0.60

 ignor

-0.58

rome

-0.57

ole

-0.57

street

-0.56

POSITIVE LOGITS

hirt

0.89

paces

0.88

ometimes

0.83

atform

0.82

hift

0.81

ilver

0.81

omething

0.77

hement

0.77

anamo

0.77

psey

0.75

Activations Density 0.349%

verbs related to movement or change of position

verbs indicating an action or participation in an event

No Comments

No Known Activations