INDEX

Explanations

Italian words or names

oai_token-act-pair · gpt-3.5-turbo

the repeated occurrence of the token "ro."

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

ivities

-0.65

 Sons

-0.64

 Catalyst

-0.63

htt

-0.62

 innocence

-0.61

HDL

-0.61

 attrition

-0.61

CTR

-0.59

 Teacher

-0.59

 Hancock

-0.58

POSITIVE LOGITS

cks

1.32

bably

1.21

chemical

1.10

phy

1.10

tto

1.09

spective

1.07

vs

1.05

blem

1.05

ds

1.04

bes

1.03

Activations Density 0.028%

Italian words or names

the repeated occurrence of the token "ro."

No Comments

No Known Activations