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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.09

4:0.09

5:0.08

6:0.08

7:0.08

8:0.08

9:0.09

10:0.07

11:0.07

Negative Logits

AMA

-2.08

Inv

-1.99

Nug

-1.77

 Ambassador

-1.71

 aliases

-1.70

 Highlights

-1.64

 ambassadors

-1.62

 patents

-1.60

Adv

-1.60

 Protect

-1.59

POSITIVE LOGITS

raq

1.98

Reviewed

1.89

CBS

1.86

cery

1.80

ordinate

1.77

yg

1.75

window

1.73

obar

1.70

jar

1.70

lled

1.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.