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

0:0.06

1:0.06

2:0.09

3:0.08

4:0.09

5:0.08

6:0.09

7:0.09

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

nosis

-2.01

amin

-1.79

STD

-1.69

ylene

-1.65

resa

-1.61

akov

-1.53

ci

-1.52

assium

-1.52

cription

-1.49

cience

-1.49

POSITIVE LOGITS

 satell

1.90

 describ

1.63

★

1.61

 Kinnikuman

1.57

BOOK

1.57

 spark

1.57

 livest

1.55

 laun

1.55

 Coul

1.53

 disag

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.