INDEX

Explanations

first person pronouns with emphasis

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.06

1:0.02

2:0.20

3:0.13

4:0.05

5:0.11

6:0.02

7:0.01

8:0.16

9:0.12

10:0.05

11:0.02

Negative Logits

emale

-1.61

ioxide

-1.41

etheus

-1.35

govtrack

-1.27

akening

-1.20

issance

-1.20

BuyableInstoreAndOnline

-1.16

adra

-1.15

 brink

-1.14

��

-1.14

POSITIVE LOGITS

 Secret

1.07

ocy

1.05

 Tong

1.04

lement

1.04

OTA

1.04

 tongue

1.02

 firsthand

1.02

Typ

1.01

 Dalai

1.00

wolves

1.00

Activations Density 0.086%

first person pronouns with emphasis

No Comments

No Known Activations