INDEX

Explanations

phrases related to describing concepts or ideas

oai_token-act-pair · gpt-3.5-turbo

the end of text markers or signify completion

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

anwhile

-0.70

emale

-0.60

vertisement

-0.57

xtap

-0.54

enegger

-0.53

allery

-0.51

ridor

-0.49

 Aware

-0.49

ornings

-0.48

 moreover

-0.47

POSITIVE LOGITS

 anymore

0.61

 crap

0.55

ratom

0.52

 shitty

0.51

 fucking

0.50

 ourselves

0.49

 shit

0.48

Pokemon

0.47

 somebody

0.47

 Allaah

0.47

Activations Density 2.013%

phrases related to describing concepts or ideas

the end of text markers or signify completion

No Comments

No Known Activations