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

0:0.08

1:0.08

2:0.08

3:0.07

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

��

-1.74

 Braun

-1.74

 Slot

-1.70

aples

-1.65

 Button

-1.65

 Dimension

-1.61

 Springer

-1.56

 Lith

-1.53

 Crusher

-1.51

 Guests

-1.50

POSITIVE LOGITS

Sov

1.86

Reviewer

1.74

1.55

 SHALL

1.51

oldemort

1.51

ieft

1.50

 disagreement

1.49

ormons

1.49

PAC

1.48

votes

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.