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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.07

5:0.08

6:0.07

7:0.08

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

��

-2.42

��

-2.06

�

-1.95

opian

-1.94

galitarian

-1.87

oples

-1.85

ONSORED

-1.82

gow

-1.82

nesota

-1.81

��

-1.78

POSITIVE LOGITS

 declass

2.20

 credited

1.82

 describ

1.81

 Blizzard

1.80

 attm

1.78

 header

1.73

 documenting

1.72

 Graveyard

1.71

 whistleblower

1.64

 slip

1.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.