INDEX

Explanations

phrases related to education and teaching

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

1:0.03

2:0.14

3:0.09

4:0.09

5:0.08

6:0.02

7:0.02

8:0.19

9:0.15

10:0.05

11:0.02

Negative Logits

ciation

-1.23

hod

-1.17

vous

-1.09

 closures

-1.08

drawn

-1.07

sov

-1.06

 torped

-1.04

 honour

-1.04

 roundup

-1.04

 abrupt

-1.02

POSITIVE LOGITS

jury

1.34

arijuana

1.26

fol

1.15

ogo

1.14

 gospel

1.11

cigarette

1.11

holiday

1.11

 skeptical

1.10

heit

1.10

isle

1.10

Activations Density 0.011%

phrases related to education and teaching

No Comments

No Known Activations