INDEX

Explanations

phrases indicating negation

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing limitations or negations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ahime

-0.71

 Presence

-0.71

iership

-0.68

lycer

-0.65

mosp

-0.65

ideon

-0.64

yss

-0.60

 Basics

-0.59

igree

-0.59

 Metatron

-0.59

POSITIVE LOGITS

xious

1.07

except

0.86

 avail

0.85

oses

0.83

ct

0.82

obs

0.79

xus

0.78

AH

0.78

vell

0.77

 longer

0.77

Activations Density 0.052%

phrases indicating negation

phrases emphasizing limitations or negations

No Comments

No Known Activations