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

1:0.09

2:0.08

3:0.09

4:0.07

5:0.07

6:0.08

7:0.06

8:0.08

9:0.09

10:0.09

11:0.08

Negative Logits

mega

-1.73

 mould

-1.58

 mainstream

-1.54

iOS

-1.54

 embodied

-1.50

 boutique

-1.50

 generational

-1.48

 Millennials

-1.47

 executable

-1.47

 domestically

-1.46

POSITIVE LOGITS

FK

2.09

voy

1.97

rimination

1.79

 Roose

1.66

hift

1.65

apter

1.65

watching

1.61

bringer

1.60

joy

1.60

Haunted

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.