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

1:0.05

2:0.08

3:0.09

4:0.09

5:0.09

6:0.08

7:0.09

8:0.09

9:0.06

10:0.08

11:0.08

Negative Logits

flation

-1.85

Ranked

-1.82

ulence

-1.81

oku

-1.68

stakes

-1.62

theme

-1.51

ishes

-1.51

topic

-1.51

oji

-1.47

terness

-1.45

POSITIVE LOGITS

Interstitial

2.08

ilant

1.66

者

1.56

 Standing

1.55

 flex

1.54

pta

1.52

psey

1.52

 WATCH

1.51

 Photographer

1.49

 arrang

1.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.