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

PlotsExplanationShow Test FieldDefault Test Text

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

5:0.06

6:0.08

7:0.11

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

jac

-1.64

 damaging

-1.58

sep

-1.58

 harmful

-1.57

 rupt

-1.55

 corros

-1.54

 walls

-1.52

Fra

-1.50

 Salv

-1.47

 decaying

-1.47

POSITIVE LOGITS

DragonMagazine

2.40

ERY

2.05

Dispatch

1.75

onomy

1.69

onomous

1.66

1.65

ynchronous

1.64

 "$:/

1.63

ケ

1.63

lance

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.