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

1:0.08

2:0.08

3:0.08

4:0.09

5:0.06

6:0.07

7:0.09

8:0.08

9:0.07

10:0.08

11:0.07

Negative Logits

 Authors

-1.84

 AUTH

-1.83

 POLIT

-1.79

 partName

-1.75

"]=>

-1.73

MpServer

-1.70

MEM

-1.68

 Bard

-1.68

 Mehran

-1.66

Nay

-1.63

POSITIVE LOGITS

 rigged

1.93

 Simulator

1.91

aco

1.82

apons

1.77

 simul

1.70

rosso

1.69

 spoof

1.68

icc

1.65

acist

1.64

 radio

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.