INDEX

Explanations

phrases indicating transformation or change

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.01

2:0.15

3:0.05

4:0.08

5:0.03

6:0.03

7:0.16

8:0.14

9:0.03

10:0.05

11:0.17

Negative Logits

 Bagg

-1.46

kit

-1.40

 Frey

-1.38

е

-1.37

 Mueller

-1.36

 Beir

-1.35

inar

-1.34

ueller

-1.34

heet

-1.32

 Fenrir

-1.29

POSITIVE LOGITS

erness

1.61

livion

1.50

lite

1.44

entric

1.43

uilt

1.42

 obscurity

1.42

levels

1.39

veyard

1.38

gypt

1.38

azard

1.36

Activations Density 0.028%

phrases indicating transformation or change

No Comments

No Known Activations