INDEX

Explanations

symbols and characters from various languages or encoding formats

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

New Auto-Interp

Top Features by Cosine Similarity

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

0:0.10

1:0.04

2:0.13

3:0.19

4:0.04

5:0.03

6:0.06

7:0.06

8:0.09

9:0.04

10:0.05

11:0.11

Negative Logits

wagen

-1.38

 simultane

-1.19

 ecstasy

-1.18

 Profile

-1.18

 Ascension

-1.15

POV

-1.14

 Closing

-1.14

holm

-1.12

 LIMITED

-1.10

 Likes

-1.09

POSITIVE LOGITS

�

1.65

�

1.55

シャ

1.53

�

1.47

luaj

1.41

ヤ

1.40

�

1.39

ケ

1.37

�

1.37

�

1.36

Activations Density 0.003%

symbols and characters from various languages or encoding formats

No Comments

No Known Activations