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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.06

2:0.07

3:0.08

4:0.07

5:0.09

6:0.09

7:0.09

8:0.09

9:0.06

10:0.09

11:0.08

Negative Logits

 Santorum

-1.73

ly

-1.61

zu

-1.53

 vomit

-1.49

ディ

-1.48

wo

-1.46

alist

-1.42

 retard

-1.41

 Haram

-1.40

phal

-1.40

POSITIVE LOGITS

————

1.88

EMBER

1.65

Thumbnail

1.63

Reward

1.56

Fram

1.53

Appearances

1.49

unta

1.47

-------------

1.45

RTX

1.45

steamapps

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.