INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

1:0.08

2:0.07

3:0.08

4:0.08

5:0.07

6:0.08

7:0.09

8:0.09

9:0.07

10:0.07

11:0.08

Negative Logits

lis

-2.72

WD

-2.62

├

-2.53

 Kelvin

-2.53

›

-2.53

wcsstore

-2.49

gre

-2.49

 Agric

-2.49

 greens

-2.45

‎

-2.44

POSITIVE LOGITS

zbollah

2.74

mble

2.45

�

2.43

luaj

2.43

 Healer

2.31

 Azerbaijan

2.21

�

2.18

 Bombs

2.14

onement

2.13

LOD

2.10

Activations Density 0.000%

No Known Activations

This feature has no known activations.