INDEX

Explanations

references to specific named entities like people, organizations, and locations

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

Ö¼

-0.52

È

-0.49

ĸ

-0.45

ļ

-0.45

istor

-0.45

*)

-0.44

Â·Â·

-0.44

ioxide

-0.44

 Examination

-0.44

POSITIVE LOGITS

 respectively

0.65

 apiece

0.59

Pac

0.46

rael

0.43

built

0.41

chedel

0.41

 Together

0.40

Hz

0.40

Fal

0.39

ijah

0.39

Activations Density 2.468%

references to specific named entities like people, organizations, and locations

No Comments

No Known Activations