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

0:0.07

1:0.07

2:0.08

3:0.09

4:0.07

5:0.07

6:0.08

7:0.08

8:0.08

9:0.09

10:0.08

11:0.08

Negative Logits

��

-3.03

 Hogan

-2.79

 mainline

-2.79

 Boxing

-2.65

Ou

-2.55

resy

-2.54

 Pagan

-2.54

 Ghostbusters

-2.53

itbart

-2.51

busters

-2.51

POSITIVE LOGITS

ゼウス

3.22

":[

3.02

 Chennai

2.99

cuc

2.89

":["

2.75

issa

2.68

 Clarke

2.56

config

2.50

intendent

2.50

Utt

2.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.