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

2:0.10

3:0.08

4:0.09

5:0.07

6:0.09

7:0.07

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

sonian

-1.92

 generously

-1.64

crim

-1.62

 freezer

-1.57

ˈ

-1.55

quartered

-1.55

 flanked

-1.53

 gorge

-1.52

 lush

-1.49

 proceeds

-1.49

POSITIVE LOGITS

Warren

1.77

 Tempest

1.76

 Remain

1.75

 Pearce

1.75

 Surviv

1.75

Higher

1.73

ה

1.65

 Oracle

1.65

 Judgment

1.59

ר

1.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.