INDEX

Explanations

names of individuals

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

0:0.07

1:0.02

2:0.10

3:0.08

4:0.08

5:0.12

6:0.02

7:0.06

8:0.10

9:0.10

10:0.14

11:0.06

Negative Logits

 suspic

-0.94

 uphill

-0.91

 asses

-0.89

 footing

-0.87

 desper

-0.86

 reluct

-0.84

 brood

-0.84

 oppress

-0.81

 corrid

-0.80

 ponies

-0.80

POSITIVE LOGITS

LLP

1.29

angan

1.26

Jr

1.25

oglu

1.25

III

1.18

(@

1.14

ér

1.05

uala

1.04

ğ

1.03

tein

1.02

Activations Density 0.708%

names of individuals

No Comments

No Known Activations