INDEX

Explanations

activities or descriptions related to coding and programming

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 unison

-0.61

their

-0.55

 prevalence

-0.53

 aggregate

-0.51

 similarity

-0.51

ASP

-0.51

 Variant

-0.51

vari

-0.51

iciency

-0.50

 defic

-0.50

POSITIVE LOGITS

 himself

1.57

his

1.15

His

1.11

 herself

1.09

 Himself

1.07

he

1.05

his

1.04

He

0.97

His

0.90

He

0.84

Activations Density 0.887%

activities or descriptions related to coding and programming

No Comments

No Known Activations