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

1:0.07

2:0.10

3:0.09

4:0.08

5:0.09

6:0.08

7:0.06

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

 forever

-1.70

 accordingly

-1.52

attach

-1.44

 cheaply

-1.44

"],"

-1.43

ipl

-1.40

 instant

-1.40

 inexpensive

-1.38

 organizers

-1.38

 cheap

-1.37

POSITIVE LOGITS

ggles

1.86

 Dating

1.62

mM

1.62

 surn

1.62

 fide

1.60

perty

1.58

axter

1.58

rait

1.54

entric

1.53

 mull

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.