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

0:0.09

1:0.04

2:0.07

3:0.07

4:0.08

5:0.09

6:0.07

7:0.09

8:0.10

9:0.08

10:0.07

11:0.10

Negative Logits

////////////////////////////////

-1.85

################################

-1.68

 mitigating

-1.67

akin

-1.64

 borne

-1.58

 squared

-1.57

iliary

-1.56

 Lauder

-1.56

 disclaim

-1.54

 fault

-1.53

POSITIVE LOGITS

print

1.80

Quantity

1.64

 preset

1.55

Icon

1.53

approved

1.49

books

1.48

Legend

1.48

println

1.46

Newsletter

1.46

Room

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.