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

0:0.10

1:0.06

2:0.08

3:0.08

4:0.08

5:0.09

6:0.07

7:0.07

8:0.10

9:0.07

10:0.08

11:0.07

Negative Logits

ocard

-1.78

 Ulster

-1.73

 Welsh

-1.69

 vanquished

-1.66

onents

-1.62

ampions

-1.61

zx

-1.55

dy

-1.55

ynes

-1.54

amus

-1.51

POSITIVE LOGITS

Untitled

2.07

�

1.75

endor

1.66

Daddy

1.64

�

1.63

 portals

1.62

Hi

1.60

龍契士

1.58

م

1.54

paralleled

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.