INDEX

Explanations

technical terms related to computing and programming

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names of notable individuals or characters

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

Interstitial

-0.76

emale

-0.68

farious

-0.60

HCR

-0.60

ĳå£«

-0.59

enegger

-0.58

 disadvant

-0.58

 Nanto

-0.57

 Palest

-0.56

 Niet

-0.56

POSITIVE LOGITS

 âĢº

0.55

helm

0.51

::

0.48

rop

0.47

Â¶

0.47

bugs

0.47

 propell

0.47

 rust

0.46

bug

0.46

 Âł

0.46

Activations Density 0.369%

technical terms related to computing and programming

proper nouns and names of notable individuals or characters

No Comments

No Known Activations