INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.06

2:0.06

3:0.08

4:0.08

5:0.08

6:0.09

7:0.08

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

ppings

-1.76

natureconservancy

-1.70

Fei

-1.60

 Subtle

-1.57

irs

-1.57

 overtly

-1.57

 preceded

-1.55

Benz

-1.48

 Emin

-1.46

aces

-1.45

POSITIVE LOGITS

tein

1.65

REDACTED

1.60

 consolation

1.54

�醒

1.46

phies

1.45

DEM

1.44

ヘ

1.43

 sqor

1.41

 starvation

1.41

 restriction

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.