INDEX

Explanations

the word "single" preceded by "every" in the text

oai_token-act-pair · gpt-3.5-turbo

the phrase "every single."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

orthy

-0.74

eln

-0.71

arty

-0.69

ORK

-0.68

ersive

-0.68

umbledore

-0.66

ual

-0.66

uay

-0.65

 exha

-0.65

POSITIVE LOGITS

THING

1.12

 digits

0.90

 digit

0.88

WHERE

0.83

 goddamn

0.79

 imaginable

0.78

 dollar

0.75

thing

0.74

body

0.73

 person

0.72

Activations Density 0.012%

the word "single" preceded by "every" in the text

the phrase "every single."

No Comments

No Known Activations