INDEX

Explanations

No Explanations Found

New Auto-Interp

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

3:0.09

4:0.08

5:0.07

6:0.08

7:0.07

8:0.09

9:0.09

10:0.09

11:0.07

Negative Logits

etc

-1.76

POV

-1.54

ults

-1.51

▬

-1.48

 Likes

-1.44

assic

-1.44

ensual

-1.44

 Played

-1.38

 exhib

-1.38

 Malk

-1.38

POSITIVE LOGITS

1.78

Pwr

1.72

abo

1.63

ashington

1.61

 advis

1.61

raft

1.60

uti

1.56

eus

1.52

Hamilton

1.50

oops

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.