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

0:0.10

1:0.07

2:0.09

3:0.08

4:0.07

5:0.09

6:0.08

7:0.07

8:0.08

9:0.07

10:0.07

11:0.09

Negative Logits

 exhib

-1.96

 dress

-1.67

esp

-1.66

ukong

-1.65

civ

-1.64

 solicit

-1.63

 Viol

-1.61

 Plaint

-1.61

 ladies

-1.58

 liber

-1.58

POSITIVE LOGITS

 WATCHED

2.31

ournal

2.08

rade

1.90

rian

1.70

grain

1.65

hammer

1.64

majority

1.57

ools

1.55

ère

1.53

solete

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.