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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.05

2:0.08

3:0.07

4:0.07

5:0.10

6:0.07

7:0.09

8:0.09

9:0.10

10:0.08

11:0.09

Negative Logits

 Madness

-1.76

 Fame

-1.67

bies

-1.65

 Wanted

-1.64

IDs

-1.64

 Legacy

-1.60

-$

-1.59

 Rapids

-1.58

 Vend

-1.57

ァ

-1.57

POSITIVE LOGITS

 retreat

2.03

 retreating

1.95

uchin

1.90

 calmly

1.71

ervation

1.56

itbart

1.50

 safer

1.50

 kettle

1.50

 downt

1.49

 recoil

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.