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

0:0.08

1:0.05

2:0.09

3:0.07

4:0.08

5:0.08

6:0.07

7:0.08

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

pee

-1.78

 liter

-1.74

 foreskin

-1.71

displayText

-1.69

 Celebr

-1.63

(&

-1.62

 gallon

-1.61

 cath

-1.59

 Unle

-1.57

IDE

-1.56

POSITIVE LOGITS

ieri

2.02

ammers

1.78

 opportun

1.63

urther

1.60

erest

1.60

chuk

1.53

 scenarios

1.52

eworks

1.52

unin

1.51

imov

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.