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

0:0.09

1:0.05

2:0.08

3:0.08

4:0.10

5:0.10

6:0.07

7:0.07

8:0.07

9:0.07

10:0.08

11:0.07

Negative Logits

 comr

-1.71

 biscuits

-1.49

 antioxid

-1.48

¯

-1.46

 bribes

-1.45

 monarch

-1.42

*)

-1.42

 compliments

-1.41

phia

-1.41

 unden

-1.41

POSITIVE LOGITS

yg

1.66

reshold

1.65

rb

1.61

ua

1.59

gger

1.59

iannopoulos

1.56

urst

1.55

scan

1.51

attr

1.50

bg

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.