INDEX

Explanations

references to natural environments, specifically forests

oai_token-act-pair · gpt-3.5-turbo

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

odder

-0.73

ampion

-0.67

ork

-0.66

bour

-0.65

rament

-0.65

ool

-0.63

Ack

-0.63

obb

-0.62

aba

-0.62

afa

-0.61

POSITIVE LOGITS

to

0.97

to

0.89

onte

0.87

 thereto

0.82

TO

0.76

)=(

0.71

 Nanto

0.70

TO

0.69

 obliged

0.68

İ

0.67

Activations Density 0.251%

references to natural environments, specifically forests

No Comments

No Known Activations