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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.10

8:0.07

9:0.07

10:0.09

11:0.09

Negative Logits

orate

-2.17

 behavi

-1.83

independent

-1.76

BIL

-1.74

government

-1.73

 minorities

-1.72

 minority

-1.70

ublic

-1.67

GOT

-1.65

 citiz

-1.64

POSITIVE LOGITS

 Illust

1.85

 Crusher

1.82

ishable

1.75

 Gloss

1.74

 engraved

1.72

 referenced

1.70

 Quartz

1.70

 Shap

1.69

 Lect

1.66

Maw

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.