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

1:0.07

2:0.09

3:0.09

4:0.08

5:0.09

6:0.08

7:0.07

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 ceremony

-1.93

 cure

-1.62

 disguise

-1.57

 pomp

-1.55

 champagne

-1.55

dye

-1.53

 Sakuya

-1.52

 pose

-1.51

 Dracula

-1.50

 assassination

-1.50

POSITIVE LOGITS

wic

2.04

ACTED

1.96

Reviewer

1.94

Avg

1.83

unity

1.75

DF

1.74

PDATE

1.71

EStreamFrame

1.68

 WATCHED

1.67

pez

1.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.