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

1:0.11

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 thinner

-1.72

illard

-1.62

itto

-1.57

 junk

-1.55

 lipstick

-1.52

middle

-1.51

 vertex

-1.50

 vert

-1.48

gum

-1.48

lip

-1.47

POSITIVE LOGITS

RIPT

2.19

HOU

2.08

1.93

onom

1.91

YR

1.85

DEM

1.85

ゴン

1.79

══

1.79

 Cosponsors

1.78

Interested

1.77

Activations Density 0.000%

No Known Activations

This feature has no known activations.