INDEX

Explanations

phrases or sentences where something is being described as expected or unsurprising

oai_token-act-pair · gpt-3.5-turbo

phrases indicating an expected outcome or event

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

audi

-0.64

oyer

-0.63

eor

-0.57

Ess

-0.57

bryce

-0.56

 Ended

-0.55

 Starts

-0.55

oller

-0.55

 Theme

-0.55

Planet

-0.55

POSITIVE LOGITS

pires

1.08

pired

0.95

 opposed

0.82

 well

0.80

phal

0.75

 follows

0.75

piration

0.69

far

0.69

 soon

0.69

 evidenced

0.68

Activations Density 0.061%

phrases or sentences where something is being described as expected or unsurprising

phrases indicating an expected outcome or event

No Comments

No Known Activations