INDEX

Explanations

the word "neither" in contrast statements

oai_token-act-pair · gpt-3.5-turbo

the word "neither" and its various contexts in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

inav

-0.76

Vers

-0.75

psc

-0.73

ahime

-0.73

 Reincarn

-0.68

ACH

-0.67

soType

-0.65

 srfAttach

-0.65

andi

-0.64

Bound

-0.64

POSITIVE LOGITS

 sexes

0.82

theless

0.78

 overtly

0.72

 genders

0.71

soever

0.71

icably

0.70

 sides

0.70

ĨĴ

0.68

 percept

0.66

!--

0.65

Activations Density 0.006%

the word "neither" in contrast statements

the word "neither" and its various contexts in sentences

No Comments

No Known Activations