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

0:0.09

1:0.07

2:0.07

3:0.08

4:0.08

5:0.07

6:0.08

7:0.07

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

alsa

-3.02

ById

-2.87

 Irving

-2.67

 Alvin

-2.67

オ

-2.63

ム

-2.60

uay

-2.59

ウス

-2.55

エル

-2.53

 Polo

-2.49

POSITIVE LOGITS

^^^^

2.88

 pancreat

2.81

ND

2.66

 rapp

2.62

Clo

2.57

 Christensen

2.55

 Traff

2.53

SCH

2.50

wat

2.48

Ye

2.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.