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

0:0.09

1:0.06

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

 pictured

-1.71

 dashed

-1.69

 ital

-1.63

 circled

-1.59

chid

-1.57

 boxed

-1.56

boo

-1.49

 Cele

-1.49

 trailed

-1.47

HH

-1.46

POSITIVE LOGITS

��

1.75

 fundament

1.69

ゴン

1.68

 Quit

1.66

 arrang

1.63

Enabled

1.61

 CONTR

1.58

gments

1.58

 sugg

1.56

edom

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.