INDEX

Explanations

the word "every" followed by another word

oai_token-act-pair · gpt-3.5-turbo

the word "every" and its variants indicating totality or universality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

olas

-0.74

 Metatron

-0.69

ket

-0.67

phabet

-0.63

Viz

-0.61

hem

-0.61

hess

-0.60

he

-0.60

dict

-0.59

 Scholars

-0.59

POSITIVE LOGITS

THING

1.36

 conceivable

0.93

where

0.92

WHERE

0.90

ursday

0.89

 imaginable

0.87

ĸļ

0.85

things

0.84

 single

0.82

Ĥİ

0.81

Activations Density 0.039%

the word "every" followed by another word

the word "every" and its variants indicating totality or universality

No Comments

No Known Activations