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

1:0.06

2:0.08

3:0.08

4:0.08

5:0.07

6:0.09

7:0.09

8:0.08

9:0.07

10:0.09

11:0.07

Negative Logits

 Discovery

-1.81

 Detention

-1.65

 Founders

-1.61

 Received

-1.58

Inv

-1.57

Ent

-1.48

 Tomorrow

-1.48

Tin

-1.44

Cap

-1.43

 Museum

-1.42

POSITIVE LOGITS

blance

2.16

istically

1.97

efficients

1.82

etting

1.82

versely

1.78

astically

1.72

iful

1.67

orically

1.65

 statistically

1.64

ifully

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.