INDEX

Explanations

instances of the word "turn"

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "turns" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

inately

-0.79

capacity

-0.74

ropolitan

-0.69

ecause

-0.68

hered

-0.67

foundation

-0.66

hammad

-0.66

anyahu

-0.64

mble

-0.64

rator

-0.63

POSITIVE LOGITS

abouts

0.91

buck

0.87

about

0.83

coat

0.81

edit

0.78

ibility

0.76

 shif

0.71

ings

0.69

ip

0.68

aho

0.68

Activations Density 0.019%

instances of the word "turn"

references to the concept of "turns" in various contexts

No Comments

No Known Activations