INDEX

Explanations

proper nouns, particularly names associated with notable individuals or entities

New Auto-Interp

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

Plots

Explanation

Show Test Field

Default Test Text

IFrame

Link

Not in Any Lists

Head Attr Weights

0:0.05

1:0.07

2:0.03

3:0.03

4:0.04

5:0.40

6:0.03

7:0.02

8:0.05

9:0.09

10:0.09

11:0.04

Negative Logits

eur

-1.67

mong

-1.66

 Alger

-1.63

 antiquity

-1.61

slaught

-1.58

iod

-1.57

 criminality

-1.52

�

-1.51

nesty

-1.50

 sinners

-1.47

POSITIVE LOGITS

*/(

2.08

 sidx

1.92

['

1.91

":[{"

1.88

rolet

1.87

Reviewer

1.75

 Motors

1.73

wcsstore

1.71

 UCHIJ

1.70

 Twins

1.70

Activations Density 0.040%

proper nouns, particularly names associated with notable individuals or entities

No Activations Uploaded