INDEX

Explanations

phrases or terms known as something specific

oai_token-act-pair · gpt-3.5-turbo

instances of the word "known" and its context of definition or description

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

rentice

-0.87

otion

-0.85

plet

-0.83

reau

-0.79

olicy

-0.79

erva

-0.76

cer

-0.75

ermanent

-0.75

ocaly

-0.73

odder

-0.72

POSITIVE LOGITS

ledged

0.90

Ð»

0.88

itarian

0.80

 abbre

0.70

 abbrevi

0.69

Els

0.69

 Known

0.68

 collectively

0.68

 aliases

0.67

 quantity

0.67

Activations Density 0.038%

phrases or terms known as something specific

instances of the word "known" and its context of definition or description

No Comments

No Known Activations