INDEX

Explanations

No Explanations Found

New Auto-Interp

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

0:0.08

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.09

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

��

-2.50

ーク

-1.71

itar

-1.70

 Seym

-1.67

iven

-1.66

vich

-1.62

ウス

-1.60

yna

-1.59

rices

-1.57

 miscar

-1.53

POSITIVE LOGITS

Joined

1.78

CVE

1.70

soType

1.62

 shelf

1.58

inventoryQuantity

1.55

Posts

1.53

REF

1.51

NOT

1.46

osponsors

1.43

bush

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.