INDEX

Explanations

terms that indicate completion or conclusion

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

0:0.07

1:0.07

2:0.08

3:0.08

4:0.09

5:0.07

6:0.07

7:0.08

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

 Gujar

-2.87

Android

-2.74

 monet

-2.67

 Android

-2.65

 concess

-2.60

Rav

-2.57

 Snapdragon

-2.52

�

-2.51

Allah

-2.50

 reper

-2.48

POSITIVE LOGITS

 Bundes

3.25

í

2.91

yre

2.79

naissance

2.78

 Asylum

2.77

 Starship

2.72

 Nightmares

2.69

Fey

2.67

 Workers

2.62

 Tourism

2.61

Activations Density 0.000%

terms that indicate completion or conclusion

No Comments

No Known Activations