INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.10

8:0.08

9:0.08

10:0.06

11:0.09

Negative Logits

Putin

-3.29

Lenin

-2.96

KGB

-2.76

 Stalin

-2.68

 Soviets

-2.68

 Soviet

-2.66

 Lenin

-2.65

MRI

-2.59

 Invaders

-2.58

с

-2.57

POSITIVE LOGITS

 fisher

2.84

inburgh

2.77

 Lilly

2.59

 Belle

2.48

 Wass

2.46

shore

2.46

�

2.43

Cly

2.41

 cider

2.38

oka

2.36

Activations Density 0.000%

No Known Activations

This feature has no known activations.