INDEX

Explanations

technical terms and acronyms

oai_token-act-pair · gpt-3.5-turbo

terms related to character traits and characteristics within a discussion context

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

SPONSORED

-0.70

Leaks

-0.68

Newsletter

-0.63

 whistlebl

-0.63

 blat

-0.62

 WATCHED

-0.59

 ÂŃ

-0.58

 nonetheless

-0.57

awed

-0.56

 expans

-0.56

POSITIVE LOGITS

trak

0.70

ackets

0.70

cens

0.65

irin

0.62

END

0.61

Tickets

0.61

 Appears

0.60

..

0.60

Mun

0.59

 Selected

0.59

Activations Density 1.035%

technical terms and acronyms

terms related to character traits and characteristics within a discussion context

No Comments

No Known Activations