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

1:0.09

2:0.09

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

 Kaufman

-1.67

asin

-1.55

Sus

-1.52

 Jacobs

-1.48

 Hogan

-1.48

Solution

-1.47

 Sieg

-1.46

 Goldberg

-1.44

 Murdoch

-1.43

 Lauder

-1.43

POSITIVE LOGITS

ノ

1.95

REDACTED

1.92

ership

1.63

Offline

1.55

Ranked

1.52

Chart

1.52

date

1.51

orical

1.48

ione

1.47

LEASE

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.