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

0:0.08

1:0.06

2:0.09

3:0.08

4:0.08

5:0.06

6:0.08

7:0.10

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

��極

-1.96

 ILCS

-1.92

ーテ

-1.78

 guiActiveUn

-1.77

alogue

-1.73

���

-1.72

soDeliveryDate

-1.70

 GEAR

-1.68

��

-1.62

 veterinarian

-1.61

POSITIVE LOGITS

stre

1.62

 unspecified

1.60

 vigorously

1.57

Interstitial

1.54

 craw

1.51

 redesigned

1.51

storms

1.49

 corrosion

1.48

ansson

1.45

 thick

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.