INDEX

Explanations

instances of the word "all"

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "at all."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

uay

-0.63

©¶æ

-0.59

pu

-0.55

uph

-0.54

Klu

-0.53

 entire

-0.52

resy

-0.52

 plank

-0.52

tru

-0.52

jected

-0.51

POSITIVE LOGITS

 times

1.01

ocating

0.93

times

0.81

 else

0.76

0.74

ãĥīãĥ©ãĤ´ãĥ³

0.74

!.

0.73

ãĢĤ

0.71

ocations

0.70

!!!!

0.70

Activations Density 0.038%

instances of the word "all"

instances of the phrase "at all."

No Comments

No Known Activations