INDEX

Explanations

verbs ending in 's' that indicate causation or influence

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate causation or effects

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

ban

-0.70

thia

-0.67

 scrimmage

-0.64

 nurs

-0.64

 Route

-0.60

---------

-0.59

 Ples

-0.59

 ILCS

-0.57

 bour

-0.56

ASE

-0.56

POSITIVE LOGITS

hift

1.22

 sure

0.98

paio

0.84

 sense

0.82

enders

0.79

arnaev

0.78

akable

0.77

ÄŁ

0.76

berra

0.74

itives

0.74

Activations Density 0.121%

verbs ending in 's' that indicate causation or influence

phrases that indicate causation or effects

No Comments

No Known Activations