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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.07

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.07

11:0.09

Negative Logits

zin

-2.90

Prince

-2.81

ISIS

-2.77

龍喚士

-2.76

atorial

-2.71

Boss

-2.70

 Bosnia

-2.68

onia

-2.67

inho

-2.58

face

-2.57

POSITIVE LOGITS

 Approach

2.82

\">

2.81

LD

2.81

\<

2.77

NBN

2.69

 estab

2.68

 Fleming

2.64

Fn

2.64

 deregulation

2.64

>)

2.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.