INDEX

Explanations

mentions of the name "ro" with various numerical values appended to it

oai_token-act-pair · gpt-3.5-turbo

references to the term "ro" or words starting with "ro"

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

 Coulter

-0.74

 Sons

-0.72

 EntityItem

-0.72

ividual

-0.68

ãĥ¼ãĥĨãĤ£

-0.68

 eminent

-0.67

arians

-0.66

 Titanic

-0.63

 Catalyst

-0.62

DPR

-0.61

POSITIVE LOGITS

spective

1.18

cks

1.11

spection

1.10

bably

1.06

blems

1.05

dden

1.02

tto

1.01

active

1.01

phant

0.99

intestinal

0.98

Activations Density 0.026%

mentions of the name "ro" with various numerical values appended to it

references to the term "ro" or words starting with "ro"

No Comments

No Known Activations