INDEX

Explanations

phrases containing the word 'and'

oai_token-act-pair · gpt-3.5-turbo

the conjunction "and" indicating connections or continuations between ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

panel

-0.67

Contents

-0.66

Â¶

-0.65

Adds

-0.63

actionDate

-0.61

ential

-0.60

ANC

-0.59

Tier

-0.59

.<

-0.58

.*

-0.57

POSITIVE LOGITS

romeda

1.04

 THEN

1.02

 then

0.96

 maybe

0.92

 blah

0.91

 therefore

0.90

 thats

0.89

 hopefully

0.86

 consequently

0.84

 secondly

0.83

Activations Density 0.762%

phrases containing the word 'and'

the conjunction "and" indicating connections or continuations between ideas

No Comments

No Known Activations