INDEX

Explanations

phrases and keywords related to performance and comparisons in various contexts

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

students' reactions or responses

oai_token-act-pair · gpt-3.5-turbo 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

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.39

2:0.07

3:0.01

4:0.01

5:0.06

6:0.05

7:0.04

8:0.05

9:0.06

10:0.08

11:0.10

Negative Logits

sonian

-1.44

 urgency

-1.32

arters

-1.31

 confirmation

-1.21

 Discuss

-1.20

 Extension

-1.19

AFB

-1.13

 Explain

-1.13

udicrous

-1.12

 release

-1.12

POSITIVE LOGITS

う

1.43

 spiritually

1.27

�

1.21

 sche

1.21

perty

1.20

Pref

1.20

really

1.19

DragonMagazine

1.19

 unfolded

1.19

Die

1.19

Activations Density 0.224%

phrases and keywords related to performance and comparisons in various contexts

students' reactions or responses

No Comments

No Known Activations