INDEX

Explanations

phrases indicating certainty or agreement

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

conversational transitions and affirmations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

Head Attr Weights

0:0.01

1:0.02

2:0.11

3:0.08

4:0.01

5:0.02

6:0.18

7:0.05

8:0.04

9:0.13

10:0.05

11:0.24

Negative Logits

SPONSORED

-1.33

zar

-1.26

psey

-1.19

hern

-1.15

comments

-1.11

Discussion

-1.09

>>\

-1.08

qqa

-1.07

ende

-1.06

Released

-1.05

POSITIVE LOGITS

Abe

1.18

 congr

1.10

 Allies

1.10

Lov

1.09

 unbeliev

1.08

 Boris

1.05

 Aber

1.04

Mik

1.02

seekers

1.02

Yog

1.02

Activations Density 0.011%

phrases indicating certainty or agreement

conversational transitions and affirmations

No Known Activations