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

1:0.06

2:0.09

3:0.07

4:0.09

5:0.08

6:0.09

7:0.09

8:0.08

9:0.06

10:0.07

11:0.08

Negative Logits

 selves

-1.95

 Olympia

-1.80

LE

-1.79

Ern

-1.78

Cub

-1.75

 Bulg

-1.73

 Devin

-1.71

 Burr

-1.71

Pau

-1.70

FN

-1.66

POSITIVE LOGITS

pse

2.27

opian

1.97

 caut

1.91

armac

1.90

 traged

1.89

ogun

1.86

terness

1.83

 lect

1.82

 guiActiveUn

1.82

xtap

1.78

Activations Density 0.000%

No Known Activations

This feature has no known activations.