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

0:0.08

1:0.05

2:0.09

3:0.07

4:0.08

5:0.08

6:0.08

7:0.08

8:0.09

9:0.08

10:0.08

11:0.09

Negative Logits

onics

-1.96

utical

-1.77

rief

-1.74

awaru

-1.73

ukemia

-1.73

other

-1.68

uther

-1.66

uristic

-1.63

oustic

-1.63

ocal

-1.62

POSITIVE LOGITS

 mole

1.58

CFR

1.56

 Rebell

1.55

tip

1.45

 worker

1.45

 poppy

1.39

 tipped

1.36

 Quit

1.35

 Yemeni

1.35

 takeoff

1.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.