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

1:0.09

2:0.08

3:0.07

4:0.09

5:0.09

6:0.08

7:0.08

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

将

-1.70

 improv

-1.63

 audition

-1.61

 interviews

-1.61

 rehears

-1.59

 premie

-1.58

 Emmy

-1.58

 listens

-1.57

 airing

-1.57

Hew

-1.55

POSITIVE LOGITS

aiden

1.88

aunted

1.85

liction

1.66

vals

1.63

zar

1.62

lance

1.59

�

1.59

ords

1.59

quartered

1.58

uchin

1.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.