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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.08

5:0.09

6:0.07

7:0.09

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

 franc

-1.65

)-

-1.61

��

-1.60

emonic

-1.56

verb

-1.54

\-

-1.51

 preferred

-1.50

 applied

-1.50

anza

-1.50

iffe

-1.49

POSITIVE LOGITS

 Empires

1.92

 Arbit

1.74

 Pharaoh

1.69

 Until

1.67

MQ

1.58

 Classification

1.56

 Anat

1.50

gradation

1.50

TOD

1.48

 Chal

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.