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

1:0.05

2:0.09

3:0.09

4:0.09

5:0.09

6:0.08

7:0.09

8:0.07

9:0.08

10:0.07

11:0.08

Negative Logits

神

-1.70

osher

-1.65

ukemia

-1.56

 Happiness

-1.55

zees

-1.54

 Diesel

-1.54

 Favorite

-1.53

vell

-1.52

 Achievement

-1.51

 Uncharted

-1.48

POSITIVE LOGITS

 documented

1.74

 immobil

1.67

 intercepted

1.63

imen

1.63

 circulated

1.62

 stopped

1.61

ylum

1.59

 encl

1.58

duration

1.57

eden

1.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.