INDEX

Explanations

passive voice constructions with the verb "said."

oai_token-act-pair · gpt-3.5-turbo

instances of the word "said" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iots

-0.64

ettlement

-0.64

Zone

-0.64

avier

-0.63

ment

-0.61

teness

-0.60

comes

-0.59

mental

-0.59

ierra

-0.59

ments

-0.58

POSITIVE LOGITS

hap

0.74

 anecd

0.72

ª

0.68

ril

0.67

 proport

0.65

 msec

0.63

entious

0.63

ocry

0.62

 Borough

0.58

ĸ

0.58

Activations Density 0.083%

passive voice constructions with the verb "said."

instances of the word "said" in various contexts

No Comments

No Known Activations