INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

1:0.08

2:0.08

3:0.08

4:0.07

5:0.07

6:0.08

7:0.08

8:0.08

9:0.09

10:0.08

11:0.09

Negative Logits

 Parties

-2.27

Row

-2.23

 Chains

-2.06

 Location

-2.05

 Downs

-1.96

 Offline

-1.93

Rs

-1.90

 Paid

-1.87

 Catal

-1.86

 Rent

-1.85

POSITIVE LOGITS

awan

2.14

eus

2.06

 counselor

1.96

 encyclopedia

1.92

 blister

1.87

 pouch

1.86

orah

1.85

fen

1.83

 probe

1.82

stellar

1.82

Activations Density 0.000%

No Known Activations

This feature has no known activations.