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

0:0.07

1:0.06

2:0.08

3:0.09

4:0.08

5:0.07

6:0.08

7:0.10

8:0.08

9:0.07

10:0.08

11:0.10

Negative Logits

 guarding

-1.79

psey

-1.66

gul

-1.58

 Lithuan

-1.57

 sighting

-1.56

 accidentally

-1.53

 Franch

-1.53

Baz

-1.50

addon

-1.47

 allegiance

-1.46

POSITIVE LOGITS

�

1.83

catentry

1.74

Bench

1.72

PLIC

1.70

ニ

1.70

TPS

1.62

nec

1.60

Financial

1.57

PDF

1.50

Pix

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.