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

1:0.04

2:0.09

3:0.07

4:0.07

5:0.07

6:0.06

7:0.07

8:0.10

9:0.08

10:0.08

11:0.10

Negative Logits

 skelet

-2.19

 subsequ

-1.76

jri

-1.76

aces

-1.71

lique

-1.70

plete

-1.70

hedral

-1.65

 contrad

-1.64

pse

-1.63

cyclopedia

-1.60

POSITIVE LOGITS

NY

1.73

 Kills

1.71

 recommends

1.57

FML

1.50

 sells

1.49

 insists

1.49

num

1.49

McF

1.49

 caller

1.49

 justifies

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.