INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

0:0.09

1:0.06

2:0.06

3:0.07

4:0.07

5:0.07

6:0.08

7:0.11

8:0.07

9:0.07

10:0.09

11:0.11

Negative Logits

OUGH

-2.47

 Author

-2.19

 fitt

-2.04

inical

-1.99

 instructional

-1.98

 Photographer

-1.98

miah

-1.96

 translator

-1.95

 Ethnic

-1.95

erton

-1.94

POSITIVE LOGITS

grab

2.25

 Cent

2.21

bomb

2.17

 thefts

2.12

 seiz

2.10

Rai

2.09

 Cerberus

2.04

obos

2.01

 plunder

2.00

 steal

1.92

Activations Density 0.000%

No Known Activations

This feature has no known activations.