INDEX

Explanations

No Explanations Found

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

0:0.08

1:0.05

2:0.10

3:0.10

4:0.09

5:0.09

6:0.06

7:0.07

8:0.08

9:0.06

10:0.07

11:0.08

Negative Logits

 IMAGES

-1.60

 parade

-1.60

 timelines

-1.60

 passer

-1.52

 Wander

-1.50

FG

-1.48

 weddings

-1.47

 chant

-1.46

 programme

-1.44

 Guinness

-1.44

POSITIVE LOGITS

��

2.14

pload

1.98

yip

1.90

edom

1.85

uin

1.78

ptr

1.77

ushi

1.76

apo

1.74

ultan

1.74

uez

1.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.