INDEX

Explanations

instances of quotations and references to quotes within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.02

2:0.08

3:0.10

4:0.02

5:0.06

6:0.10

7:0.26

8:0.07

9:0.05

10:0.08

11:0.10

Negative Logits

FTWARE

-1.32

NetMessage

-1.27

sbm

-1.19

ウス

-1.15

akeru

-1.10

ELE

-1.08

 servicing

-1.07

DEV

-1.06

FML

-1.05

schild

-1.02

POSITIVE LOGITS

 quotation

1.32

 quoted

1.30

acket

1.26

jab

1.20

 ital

1.18

 verse

1.17

 retweet

1.13

afort

1.12

 quote

1.09

 narration

1.07

Activations Density 0.020%

instances of quotations and references to quotes within the text

No Comments

No Known Activations