INDEX

Explanations

references to the letter 'E' followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

mentions of the letter "E" 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Anthem

-0.70

 patri

-0.64

 Ashton

-0.63

 Kenobi

-0.62

 names

-0.61

 redistributed

-0.60

 illusion

-0.59

 pains

-0.59

 Miranda

-0.59

EMS

-0.59

POSITIVE LOGITS

ighty

1.32

fficient

1.31

nerg

1.29

cosystem

1.28

ASY

1.26

tymology

1.21

isner

1.21

thereal

1.15

ileen

1.14

minent

1.14

Activations Density 0.029%

references to the letter 'E' followed by a numerical value

mentions of the letter "E" in various contexts

No Comments

No Known Activations