INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

0:0.06

1:0.07

2:0.08

3:0.09

4:0.10

5:0.07

6:0.08

7:0.09

8:0.08

9:0.06

10:0.07

11:0.08

Negative Logits

 bargain

-1.77

 Scrolls

-1.74

 manuscripts

-1.67

 investigating

-1.60

 forecasting

-1.55

 readers

-1.51

 trillions

-1.51

 honorable

-1.51

 convent

-1.50

 dynasty

-1.48

POSITIVE LOGITS

ーティ

2.31

�

2.02

SHIP

2.01

veh

1.98

ーテ

1.93

iaz

1.90

license

1.89

FIG

1.89

 Logged

1.87

rex

1.84

Activations Density 0.000%

No Known Activations

This feature has no known activations.