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

Head Attr Weights

0:0.07

1:0.05

2:0.08

3:0.08

4:0.10

5:0.07

6:0.08

7:0.09

8:0.08

9:0.07

10:0.10

11:0.07

Negative Logits

Prem

-1.73

 conflicting

-1.71

 unden

-1.65

Leaks

-1.62

jri

-1.56

 palpable

-1.55

 contradictions

-1.51

 ripple

-1.51

 ultras

-1.51

 procedural

-1.51

POSITIVE LOGITS

trak

2.07

acht

1.73

fit

1.60

fits

1.55

service

1.52

Favorite

1.48

 hires

1.46

 Scout

1.45

alty

1.44

utterstock

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.