INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.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

1:0.07

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

 Delhi

-3.06

 Riyadh

-2.85

 Commit

-2.84

 Trudeau

-2.83

 Pref

-2.68

 Islamabad

-2.67

 Relative

-2.62

 Punjab

-2.59

 guid

-2.57

 Ottawa

-2.56

POSITIVE LOGITS

atom

3.85

··

3.22

ynes

2.96

onew

2.96

answered

2.76

yg

2.63

Crash

2.63

izabeth

2.61

Boot

2.60

 Schwarz

2.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.