INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

3:0.09

4:0.09

5:0.07

6:0.07

7:0.09

8:0.08

9:0.08

10:0.06

11:0.09

Negative Logits

 whistle

-1.54

 Controlled

-1.42

 Calais

-1.39

Independent

-1.38

Lear

-1.38

-1.37

 junior

-1.34

 Infrastructure

-1.34

Minor

-1.33

 Falk

-1.32

POSITIVE LOGITS

advertisement

1.81

argon

1.74

escription

1.71

halla

1.70

 Pengu

1.64

 nutshell

1.63

iqueness

1.57

berman

1.54

ghai

1.53

heng

1.50

Activations Density 0.000%

No Known Activations

This feature has no known activations.