INDEX

Explanations

mentions related to legal actions or authorities seizing items

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "have" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

eem

-0.66

wrap

-0.63

amd

-0.61

ove

-0.61

 Kills

-0.61

 Place

-0.60

/+

-0.60

âĻ¦

-0.58

mast

-0.58

oyer

-0.57

POSITIVE LOGITS

 been

1.27

 begun

1.16

 tended

1.06

 reacted

1.05

 complained

1.04

 prolifer

1.03

 risen

1.03

 fared

1.02

 undergone

1.02

 gotten

1.01

Activations Density 0.227%

mentions related to legal actions or authorities seizing items

the repeated use of the word "have" in various contexts

No Comments

No Known Activations