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

2:0.09

3:0.08

4:0.07

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 Hawking

-1.72

 Commodore

-1.65

zilla

-1.55

 Trident

-1.52

Geh

-1.52

 SpaceX

-1.52

 paralyzed

-1.48

 Psychiatric

-1.48

 Lauder

-1.43

 Ministers

-1.43

POSITIVE LOGITS

 ingred

1.89

thy

1.87

iffe

1.85

abre

1.84

dirty

1.82

Lean

1.82

 confir

1.80

SPONSORED

1.70

adena

1.69

tein

1.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.