INDEX

Explanations

the word "only" in the text

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.08

1:0.09

2:0.08

3:0.08

4:0.07

5:0.07

6:0.07

7:0.09

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

►

-2.99

 Cancel

-2.80

################

-2.75

 stockp

-2.67

 RELEASE

-2.60

URRENT

-2.58

>>>>

-2.52

 Relief

-2.52

�

-2.51

ة

-2.48

POSITIVE LOGITS

orum

2.94

 Vega

2.74

 Rossi

2.69

 sails

2.69

 Ogre

2.65

 Decker

2.63

anian

2.62

 Pose

2.60

 Athena

2.58

 Penguins

2.57

Activations Density 0.000%

the word "only" in the text

No Comments

No Known Activations