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

0:0.07

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.09

7:0.08

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

ounced

-1.65

 helicop

-1.63

 ridic

-1.62

wered

-1.58

ought

-1.58

lig

-1.57

founded

-1.56

aped

-1.52

]}

-1.52

 undisclosed

-1.49

POSITIVE LOGITS

 ILCS

1.88

 Occupations

1.74

 Statistical

1.73

 Codex

1.72

 Stability

1.71

 Kingdoms

1.65

 Idle

1.65

Fem

1.65

 Transactions

1.64

 Trin

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.