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

1:0.12

2:0.08

3:0.07

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

etheless

-2.00

 Interior

-1.74

CPC

-1.65

 repaired

-1.57

DERR

-1.55

llor

-1.49

 Legions

-1.47

 rushed

-1.45

Slot

-1.45

 Legion

-1.40

POSITIVE LOGITS

�

1.83

names

1.66

✓

1.59

baugh

1.58

pak

1.58

TOP

1.57

lets

1.56

idae

1.55

gar

1.55

ser

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.