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

0:0.07

1:0.09

2:0.09

3:0.07

4:0.08

5:0.08

6:0.08

7:0.09

8:0.07

9:0.08

10:0.07

11:0.07

Negative Logits

 Manufacturer

-1.70

DOD

-1.60

 Carbuncle

-1.56

う

-1.53

���

-1.48

 Ezekiel

-1.47

 membranes

-1.45

 Constable

-1.45

 contamination

-1.45

 defective

-1.44

POSITIVE LOGITS

img

1.79

yg

1.72

roit

1.71

 vict

1.70

pless

1.67

yss

1.66

winner

1.65

ocene

1.65

yt

1.64

imeo

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.