INDEX

Explanations

instances of ordinal numbers

oai_token-act-pair · gpt-3.5-turbo

references to the concept of 'second' or 'second place'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

mercial

-0.71

Ĥİ

-0.54

ateur

-0.50

 sqor

-0.50

contract

-0.50

protein

-0.49

ateurs

-0.48

opol

-0.48

nit

-0.48

kinson

-0.47

POSITIVE LOGITS

akra

0.58

ighty

0.57

 explan

0.56

endment

0.55

{*

0.55

ipop

0.54

ciation

0.54

 behav

0.53

aft

0.52

JV

0.52

Activations Density 1.732%

instances of ordinal numbers

references to the concept of 'second' or 'second place'

No Comments

No Known Activations