INDEX

Explanations

words related to a specific character or concept, often denoted by the letter "R" followed by a number

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "R" 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 @ 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

terson

-0.74

 Coral

-0.68

 Nieto

-0.67

 Totem

-0.67

ãĥ¼ãĥĨãĤ£

-0.67

 Dolphin

-0.67

 quantity

-0.64

 Garmin

-0.63

CPR

-0.63

creen

-0.63

POSITIVE LOGITS

ansom

1.27

outine

1.24

ascal

1.22

senal

1.21

haps

1.18

oxy

1.12

ushing

1.10

attle

1.08

ifles

1.08

otten

1.08

Activations Density 0.040%

words related to a specific character or concept, often denoted by the letter "R" followed by a number

occurrences of the letter "R" in various contexts

No Comments

No Known Activations